© 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. 27736
    Prev
    Next
    INDEX
    Explanations

    blockbuster

    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
    usc
    -0.09
    èĽĨ
    -0.09
    ä¸Ĭæľī
    -0.08
    Ñħод
    -0.08
    rd
    -0.08
    бÑĢоÑģ
    -0.08
    een
    -0.08
    ä¸ľè¥¿
    -0.08
    еÑģÑĮ
    -0.08
    è°Ĺ
    -0.08
    POSITIVE LOGITS
    æŀ¶åŃIJ
    0.11
    ous
    0.09
    æŁ¥çľĭåħ¨æĸĩ
    0.09
    èŀ¯
    0.09
    owy
    0.09
    åıįåĢĴ
    0.08
    çļĦç§ĺå¯Ĩ
    0.08
     займ
    0.08
    æ¶Įåħ¥
    0.08
    è¿ĺæĺ¯è¦ģ
    0.08
    Activations Density 0.001%

    No Known Activations