© 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. 1932
    Prev
    Next
    INDEX
    Explanations

    West Virginia and state abbreviations

    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
    ли
    -0.10
    èħĻ
    -0.09
    оваÑĢ
    -0.09
    åįģå¤ļå¹´
    -0.09
    éļľç¢į
    -0.09
    ели
    -0.08
    岬
    -0.08
    à¸ģาย
    -0.08
    åIJijå¾Ģ
    -0.08
    INET
    -0.08
    POSITIVE LOGITS
    ä¼Ĺ
    0.11
    æĸ°éĹ»ç½ij
    0.10
    æĢİä¹Ī说
    0.09
    odka
    0.09
     drip
    0.08
    æݾ
    0.08
    绣çŃ¹æİ¨è¿Ľ
    0.08
    好å¤ļ
    0.08
    struments
    0.08
    ibur
    0.08
    Activations Density 0.003%

    No Known Activations