Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 36315
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Insurance
    -0.07
    DataGridView
    -0.07
     bursting
    -0.07
    清华大学
    -0.07
    umes
    -0.06
     Aber
    -0.06
     acquaintance
    -0.06
    ****************************************************************
    -0.06
    我和
    -0.06
    没想到
    -0.06
    POSITIVE LOGITS
    ($
    0.07
    提供了
    0.06
     Gain
    0.06
     Desert
    0.06
    density
    0.06
    提升了
    0.06
    _VARIABLE
    0.06
    .${
    0.06
    .(
    0.06
     sanity
    0.06
    Activations Density 0.007%

    No Known Activations