© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 34554
    Prev
    Next
    INDEX
    Explanations

    detective, hunter, or inspector characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    à¹Ĩ
    -0.08
    åıijå±ķ
    -0.08
     ба
    -0.08
    ellers
    -0.08
    åĿij
    -0.08
    åī§
    -0.08
    olt
    -0.08
     Saunders
    -0.08
    骡
    -0.08
    éģĹ
    -0.08
    POSITIVE LOGITS
    archives
    0.09
    äºijéĽĨ
    0.09
    .gov
    0.09
    ä¸Ĭåı¸
    0.08
     ust
    0.08
    éľģ
    0.08
    /owl
    0.08
    Trademark
    0.08
     dõ
    0.08
    çľĭ好
    0.08
    Activations Density 0.043%

    No Known Activations