© 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. 30922
    Prev
    Next
    INDEX
    Explanations

    Chir- or Chim- followed by suffixes

    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
    enheim
    -0.11
    YTE
    -0.10
    mente
    -0.09
    à¸Ĺรà¸ĩ
    -0.09
    èĤ¢
    -0.09
    åĩºåıij
    -0.09
    COMM
    -0.09
    ÎŃ
    -0.08
     Cand
    -0.08
    coon
    -0.08
    POSITIVE LOGITS
    äººæł¼
    0.12
    橱
    0.10
    ราย
    0.10
    ingly
    0.10
    éĤ£ä¸Ģ天
    0.09
    äºĨä¸Ģ声
    0.09
    sticks
    0.09
    bell
    0.09
    åĩłåı¥
    0.09
    punk
    0.09
    Activations Density 0.006%

    No Known Activations