© 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 EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 113343
    Prev
    Next
    INDEX
    Explanations

    article titles

    np_max-act · gemini-2.0-flash

    The neuron detects article or section headlines — the title/heading tokens that mark the start of a news item or page section.

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .syn
    -0.08
    .RemoveAll
    -0.07
    ل
    -0.07
    LK
    -0.07
     lok
    -0.06
     Ln
    -0.06
    golden
    -0.06
    可行
    -0.06
     Müd
    -0.06
    améli
    -0.06
    POSITIVE LOGITS
    世家
    0.08
    〟
    0.07
    不停地
    0.07
    (('
    0.07
    讧
    0.06
    _send
    0.06
    �장
    0.06
     coder
    0.06
    صدر
    0.06
     shoe
    0.06
    Activations Density 0.033%

    No Known Activations