© 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. 31566
    Prev
    Next
    INDEX
    Explanations

    command-line arguments and options

    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
    æĻ¡
    -0.11
    @js
    -0.10
    _TYPED
    -0.09
    çĽ¸ä¼´
    -0.09
    æªĢ
    -0.09
    åĹŁ
    -0.09
    åĻ¬
    -0.09
    ç¢Ľ
    -0.09
    æݾ
    -0.09
    eti
    -0.09
    POSITIVE LOGITS
    çı
    0.08
    èĩªæĿ¥
    0.08
    å¯Įè£ķ
    0.08
    AndWait
    0.08
    board
    0.08
    åIJ¸åıĸ
    0.08
     board
    0.07
    é¦į
    0.07
     Tok
    0.07
    æĭĽ
    0.07
    Activations Density 0.595%

    No Known Activations