© 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. 54574
    Prev
    Next
    INDEX
    Explanations

    comma separated values

    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
    _POINTER
    -0.09
     tad
    -0.09
     cps
    -0.09
     Concord
    -0.09
     PIL
    -0.08
    urator
    -0.08
    åľĨ满å®ĮæĪIJ
    -0.08
    /effects
    -0.08
     Commons
    -0.08
    é£İæ°Ķ
    -0.08
    POSITIVE LOGITS
    æ·¦
    0.11
    æī«ä¸Ģæī«
    0.10
    ç»ıèIJ¥èĮĥåĽ´
    0.10
    åĨĽåĽ¢
    0.09
    ç¢İçīĩ
    0.09
    çİĭåĽ½
    0.09
    æ¸ħåįİ
    0.08
    å«Ķ
    0.08
    åĬłçıŃ
    0.08
    åīįæıIJæĺ¯
    0.08
    Activations Density 0.188%

    No Known Activations