© 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. 11720
    Prev
    Next
    INDEX
    Explanations

    `gallery/show`

    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
    à¹īว
    -0.07
    ewith
    -0.07
    åľ¨ä»ĸçļĦ
    -0.07
    游åĩ»éĺŁ
    -0.07
     âĢ¦↵↵
    -0.07
    ä»ĸå¦Ī
    -0.07
    è§Į
    -0.07
     Rae
    -0.07
    {_
    -0.07
    åľ¨åľ°ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    ä¹Łæĺ¯å¦ĤæѤ
    0.11
    âĸ¢
    0.08
    æ¿¡
    0.08
    âĦ¯
    0.08
    åī©ä¸ĭ
    0.08
    工信éĥ¨
    0.08
    âĪľ
    0.08
    eny
    0.08
    uchen
    0.08
    ailable
    0.08
    Activations Density 1.190%

    No Known Activations