© 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. 61929
    Prev
    Next
    INDEX
    Explanations

    make you want

    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
    åĿļæĮģ以
    -0.10
    çĶ¨å¿ĥ
    -0.09
    å·¥ç¨ĭæĬĢæľ¯
    -0.09
    寻æ±Ĥ
    -0.09
    è·¨è¶Ĭ
    -0.08
    éĩįä¸Ń
    -0.08
    ä¸į好
    -0.08
    éĻª
    -0.08
    uhl
    -0.08
     sát
    -0.08
    POSITIVE LOGITS
    诱人
    0.11
    诱æĥij
    0.11
    欲
    0.10
    å¼ķ
    0.10
    说æľį
    0.10
    å¿ĥåĬ¨
    0.10
    羡
    0.10
    åIJĮèĥŀ
    0.10
    é¦ĭ
    0.09
     convin
    0.09
    Activations Density 0.081%

    No Known Activations