© 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. 33722
    Prev
    Next
    INDEX
    Explanations

    Paul, Corbyn

    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
    å¼ĤæĢ§
    -0.09
    ope
    -0.09
    æģĭ人
    -0.09
    æĬ¥ç¤¾
    -0.08
    èĢģåŃĹåı·
    -0.08
     fug
    -0.08
     ones
    -0.08
     Reb
    -0.08
    ABS
    -0.08
    ILA
    -0.08
    POSITIVE LOGITS
    isma
    0.10
    é»Ħéĩij
    0.10
    cken
    0.09
    窥
    0.09
    pto
    0.09
    æĿĥ
    0.09
    ownership
    0.09
    ç»ıæµİå¢ŀéķ¿
    0.08
     Killer
    0.08
    æ¯Ĺ
    0.08
    Activations Density 0.002%

    No Known Activations