© 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. 22631
    Prev
    Next
    INDEX
    Explanations

    names and identifiers

    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
    å¢ħ
    -0.11
    å¹³æŶ
    -0.09
    毯
    -0.09
    æ±Łä¸ľ
    -0.09
    _hdl
    -0.09
    åı¯æĥ³èĢĮçŁ¥
    -0.08
    ä¸ĬäºĨ
    -0.08
    æķĻçłĶ
    -0.08
    çļĦåĵģçīĮ
    -0.08
    è¿Ļä¸įæĺ¯
    -0.08
    POSITIVE LOGITS
     erm
    0.10
    ucz
    0.09
    åİŁåŀĭ
    0.09
    æ¸´æľĽ
    0.09
    ãĥ¬ãĥ³
    0.09
    èı±
    0.08
    oot
    0.08
     loan
    0.08
    /inet
    0.08
     Cá
    0.08
    Activations Density 0.123%

    No Known Activations