© 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. 55013
    Prev
    Next
    INDEX
    Explanations

    District of Columbia

    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
    笳
    -0.10
    èģĶåIJĪä¼ļ
    -0.09
    èģ¯åIJĪ
    -0.09
    ziel
    -0.08
     GAR
    -0.08
    ckt
    -0.08
    Õª
    -0.08
    icing
    -0.08
    èį¡
    -0.08
    iect
    -0.08
    POSITIVE LOGITS
    ç¢Į
    0.09
    åĬŃ
    0.09
    FileVersion
    0.09
    åįĬå¤ľ
    0.09
    è¶ĬæĿ¥è¶Ĭå°ij
    0.08
    _rng
    0.08
    èĻº
    0.08
    注éĶĢ
    0.08
    çł´ç¢İ
    0.08
    ç§ijçłĶéĻ¢
    0.08
    Activations Density 0.013%

    No Known Activations