© 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. 57501
    Prev
    Next
    INDEX
    Explanations

    `C:\` file paths

    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
    æĶĺ
    -0.09
    è¡Įèµ°
    -0.09
    [".
    -0.09
    ÑĨов
    -0.09
    Orm
    -0.09
    .nih
    -0.09
    ï¸
    -0.09
    leh
    -0.09
    æľ¦èĥ§
    -0.08
    ä¸ĭåįĬåľº
    -0.08
    POSITIVE LOGITS
    æ³Ľ
    0.09
     Omar
    0.09
    alcon
    0.09
    åľ°åĮºçļĦ
    0.09
    ç§ijåѦéĻ¢
    0.08
    Ùģائ
    0.08
    éĶ¦ç»£
    0.08
     Serializer
    0.08
    ä½įç½®
    0.08
    é¢ł
    0.08
    Activations Density 0.141%

    No Known Activations