© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7197
    Prev
    Next
    INDEX
    Explanations

    make-up and costume

    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
    ä¸ĩåħ¬éĩĮ
    -0.10
    è§Ħ
    -0.10
    Ĩµ
    -0.09
    ä»ĸä¹Ł
    -0.09
     entr
    -0.09
    ä¸Ģè¡Į
    -0.09
     ÑģÑĤÑĢан
    -0.09
    失
    -0.09
     кÑĥÑĢÑģ
    -0.09
    erule
    -0.09
    POSITIVE LOGITS
    å¦Ĩ
    0.10
    å½±
    0.09
    gar
    0.09
    容
    0.09
    ç¬ĭ
    0.08
    访
    0.08
    嫦
    0.08
     cosplay
    0.08
    æľįè£ħ
    0.08
    éļ¾æ°ij
    0.08
    Activations Density 0.066%

    No Known Activations