© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9641
    Prev
    Next
    INDEX
    Explanations

    following "below"

    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
    æ¶Ī
    -0.11
    icao
    -0.10
    ä¸Ģä¸ĭåŃIJå°±
    -0.09
    den
    -0.08
    éri
    -0.08
    .AutoScaleMode
    -0.08
     Conrad
    -0.08
    ey
    -0.08
    æľ«ç«¯
    -0.08
    anders
    -0.08
    POSITIVE LOGITS
    ç¾İå¦Ļ
    0.09
    æĶ¹éĿ©åıijå±ķ
    0.09
    å·¥ç¨ĭ建设
    0.09
    ä¸ĭçıŃ
    0.09
    åģ¶
    0.09
    Getter
    0.08
    宪
    0.08
    èĴ²
    0.08
    çİĦ
    0.08
    èIJ½åı¶
    0.08
    Activations Density 0.004%

    No Known Activations