© 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. 4799
    Prev
    Next
    INDEX
    Explanations

    times and durations

    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
     kans
    -0.09
    çŃł
    -0.09
    æ³ķåħ°
    -0.09
    大çIJĨ
    -0.08
    ç³Ł
    -0.08
    å»ī
    -0.08
     nghiá»ĩp
    -0.08
    åĪ°æľŁ
    -0.08
    bor
    -0.08
    /latest
    -0.08
    POSITIVE LOGITS
    æ¯ĶæĪij
    0.11
    äºĨä¸Ģåı£
    0.09
    è·Ŀ离
    0.09
    顽强
    0.09
     Tod
    0.09
    æķ´
    0.08
    å¸ĮæľĽèĩªå·±
    0.08
    çļĦç¾İ好
    0.08
    举è¡ĮäºĨ
    0.08
     Sho
    0.08
    Activations Density 0.144%

    No Known Activations