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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 42117
    Prev
    Next
    INDEX
    Explanations

    Technical documents

    np_max-act · gemini-2.0-flash

    markers indicating assistant turns in chat-style transcripts, especially the assistant role header lines.

    oai_token-act-pair · gpt-5Triggered 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
     Government
    -0.07
    эфф
    -0.07
     afore
    -0.07
    被告
    -0.07
    ﲑ
    -0.07
     sóng
    -0.07
    حكيم
    -0.07
    chant
    -0.07
     defendants
    -0.06
    auses
    -0.06
    POSITIVE LOGITS
     deepest
    0.07
    _px
    0.07
    细节
    0.07
    /copyleft
    0.07
     Located
    0.07
     minimalist
    0.07
    ENTION
    0.07
     locations
    0.06
     NX
    0.06
    青春
    0.06
    Activations Density 0.106%

    No Known Activations