© 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. 39413
    Prev
    Next
    INDEX
    Explanations

    Ace, King, heart, end, mill

    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
    绳
    -0.10
    åįĩéĻį
    -0.09
    åİ
    -0.09
    å¼Ģåĩº
    -0.09
    timing
    -0.08
    Guy
    -0.08
     Barnes
    -0.08
     Finger
    -0.08
    人身
    -0.08
    <decltype
    -0.08
    POSITIVE LOGITS
    -Ta
    0.10
    طب
    0.09
    /tutorial
    0.09
    _POWER
    0.09
    ä¸į足
    0.09
    æŶéļĶ
    0.09
    ç¾İ女
    0.09
    åѤåįķ
    0.09
    eat
    0.08
     اÙĦØŃÙħÙĦ
    0.08
    Activations Density 0.012%

    No Known Activations