© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 70696
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron detects the assistant speaker token / the start of assistant responses (i.e., text produced by the assistant).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _generator
    -0.06
    🧘
    -0.06
     h
    -0.06
     demanded
    -0.06
     estr
    -0.06
     Benedict
    -0.06
    -pos
    -0.06
    Kate
    -0.06
    (isinstance
    -0.06
     hospitality
    -0.06
    POSITIVE LOGITS
     Ủ
    0.07
    finger
    0.07
    .fn
    0.07
    /video
    0.07
    _footer
    0.07
    atile
    0.07
    cao
    0.07
     Qaeda
    0.07
    蹲
    0.07
    otti
    0.07
    Activations Density 0.036%

    No Known Activations