© 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. 48956
    Prev
    Next
    INDEX
    Explanations

    medical and academic fields

    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
    é¢ĺ
    -0.09
    vio
    -0.09
    ç´ł
    -0.09
    æŀķ
    -0.09
    tte
    -0.08
    PBS
    -0.08
    untime
    -0.08
     Ñģебе
    -0.08
    ä¼ij
    -0.08
    è½°
    -0.08
    POSITIVE LOGITS
    åIJĮå¿Ĺ们
    0.09
    èĻ¢
    0.09
    èĩªæľī
    0.09
    è¿Ľé©»
    0.09
    ç»·
    0.08
    çİĭåŃIJ
    0.08
    ç®Ń
    0.08
     Asi
    0.08
    hydr
    0.08
    å®ĮäºĨ
    0.08
    Activations Density 0.121%

    No Known Activations