© 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. 34652
    Prev
    Next
    INDEX
    Explanations

    Dodd-Frank, Cosby Show, Sporting Goods

    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
     bail
    -0.09
    stag
    -0.08
    åħĭ
    -0.08
    ç´ł
    -0.08
    ailer
    -0.08
     prick
    -0.08
    æŁ
    -0.08
    éŃĶ鬼
    -0.08
    æģ°æģ°
    -0.08
     stag
    -0.08
    POSITIVE LOGITS
    ãģĨãģ¡
    0.10
    è¡·
    0.09
    çĿļ
    0.09
    饱满
    0.09
    å½ĵçĦ¶
    0.09
    å¤ĸ交
    0.08
    atively
    0.08
    åŀ¢
    0.08
    è´¢çī©
    0.08
    æĺ¾ç¤ºåĻ¨
    0.08
    Activations Density 0.002%

    No Known Activations