© 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. 61328
    Prev
    Next
    INDEX
    Explanations

    excuses for attacking men

    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
    åĥ¦
    -0.09
    æŃĮ
    -0.09
    rape
    -0.09
     ru
    -0.09
    两èĢħ
    -0.09
    rum
    -0.09
    Ñħа
    -0.09
    羸
    -0.08
     Conce
    -0.08
    æ¾Ī
    -0.08
    POSITIVE LOGITS
    æľ¬è½®
    0.08
    åĪ«äºº
    0.08
    ç©¿æ¢Ń
    0.08
    æ¬łç¼º
    0.08
    æļ´
    0.08
     Nottingham
    0.08
    ""
    0.08
    ''
    0.08
    ä¿Ŀ
    0.07
    代çIJĨ人
    0.07
    Activations Density 0.049%

    No Known Activations