© 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. 39823
    Prev
    Next
    INDEX
    Explanations

    American Medical Association recommends

    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
    åĽĽèĤ¢
    -0.09
    snap
    -0.08
    åħµ
    -0.08
    åIJĦé¡¹å·¥ä½ľ
    -0.08
    ай
    -0.08
     дела
    -0.08
     promo
    -0.08
    ulan
    -0.08
    äºĭä¸ļåįķä½į
    -0.08
    éĩĩéĽĨ
    -0.08
    POSITIVE LOGITS
    éķĵ
    0.09
    uart
    0.09
    å¾®å¦Ļ
    0.09
     onRequest
    0.09
    olson
    0.09
    æį»
    0.09
    ulls
    0.08
    æŀĩ
    0.08
    åįĹå±±
    0.08
    ends
    0.08
    Activations Density 0.032%

    No Known Activations