© 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. 3882
    Prev
    Next
    INDEX
    Explanations

    preventive health care

    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
    åİ»åĮ»éĻ¢
    -0.10
    溷
    -0.09
    å®īçĦ¶
    -0.09
     dl
    -0.09
    è¯ī
    -0.08
    umbo
    -0.08
    å½¹
    -0.08
    ä¾Ī
    -0.08
    认åı¯
    -0.08
    sla
    -0.08
    POSITIVE LOGITS
    渣
    0.09
     forg
    0.09
    æł¼å¤ĸ
    0.08
    ä¼ļå±ķ
    0.08
    uya
    0.08
    ä¼ĺåħĪ
    0.08
    @qq
    0.08
    ç©°
    0.08
    bage
    0.08
    icken
    0.08
    Activations Density 0.213%

    No Known Activations