© 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. 18134
    Prev
    Next
    INDEX
    Explanations

    even qualified

    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
    åī¯
    -0.11
    éŀŃ
    -0.10
    ç±į
    -0.10
    ç§ijçłĶéĻ¢æīĢ
    -0.08
    unday
    -0.08
    åºĶæĢ¥ç®¡çIJĨ
    -0.08
    躺
    -0.08
    弯
    -0.08
    _readable
    -0.08
    UDGE
    -0.08
    POSITIVE LOGITS
    大èĥĨ
    0.10
    å°½æĥħ
    0.09
    å¼Ģçİ©ç¬ij
    0.09
    åį³ä½¿æĺ¯
    0.08
    èĢģ大
    0.08
    ç¨įç¨į
    0.08
    ç¿Ĭ
    0.08
    è°Ĥ
    0.08
    ä¸ĢæĹ¥
    0.08
    ä¸ĢåIJį
    0.08
    Activations Density 0.027%

    No Known Activations