© 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. 54442
    Prev
    Next
    INDEX
    Explanations

    , rare, responsive

    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
    udos
    -0.09
    /AP
    -0.09
    çĺ¿
    -0.08
    ugal
    -0.08
    å½Ģ
    -0.08
    èĴ
    -0.08
    몽
    -0.08
     дов
    -0.08
    enders
    -0.08
    ->__
    -0.08
    POSITIVE LOGITS
     etc
    0.08
     Kra
    0.08
    åıªå¥½
    0.08
    ãģ¨ãģĦãģ£ãģŁ
    0.08
    å¤ĦåĪĨ
    0.08
    æĹħ游度åģĩ
    0.07
    çŃīæĸ¹éĿ¢
    0.07
    æľĢéĩįè¦ģ
    0.07
     until
    0.07
     rubbish
    0.07
    Activations Density 0.607%

    No Known Activations