© 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. 63257
    Prev
    Next
    INDEX
    Explanations

    daily updates and archives

    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
    åİĨæĿ¥
    -0.10
    年度
    -0.10
    饰
    -0.10
    ä¸ĢåĪĩéĥ½
    -0.10
    ãģ«è¡Įãģ£ãģŁ
    -0.09
     altogether
    -0.09
    гÑĥ
    -0.09
     anytime
    -0.09
    åħ¨éĿ¢åıijå±ķ
    -0.09
    æķ´ä¸ª
    -0.09
    POSITIVE LOGITS
    ìĶ©
    0.10
    ç¹ĩ
    0.09
    é£İåIJ¹
    0.08
    bai
    0.08
    ê¼´
    0.08
    uv
    0.08
    æ¯ı天éĥ½
    0.08
    ðŁĵ°
    0.08
    (Optional
    0.08
    æīĵåį¡
    0.08
    Activations Density 0.152%

    No Known Activations