© 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. 23244
    Prev
    Next
    INDEX
    Explanations

    doing yourself favors, curiosity, help out

    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
    รà¸Ńà¸ĩ
    -0.09
    ocker
    -0.09
    迪
    -0.08
    breaker
    -0.08
    ded
    -0.08
    èģĺ
    -0.08
    åłĨ
    -0.08
    èĭ±
    -0.08
     Median
    -0.08
     beau
    -0.08
    POSITIVE LOGITS
    ç»´å¥ĩ
    0.09
    BU
    0.09
    ìĬ¤íĥĢ
    0.09
    没人
    0.08
    pain
    0.08
    åģľä¸ĭæĿ¥
    0.08
    mtx
    0.08
    æĻļå¹´
    0.08
    æŁ¥éĺħ
    0.08
    _blk
    0.08
    Activations Density 0.009%

    No Known Activations