© 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. 57075
    Prev
    Next
    INDEX
    Explanations

    surname or given name from Hebrew/Romance origins

    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
    pter
    -0.09
    åı°è¯į
    -0.09
    chor
    -0.08
    屿
    -0.08
    çĶ¨å·¥
    -0.08
    ubit
    -0.08
    kek
    -0.08
    Consum
    -0.08
    齿
    -0.08
     Termin
    -0.08
    POSITIVE LOGITS
    æ´ŀå¯Ł
    0.10
    quan
    0.09
    åľ¨åĽ½å¤ĸ
    0.09
    .variant
    0.09
    æģ³
    0.09
     Coul
    0.08
    OUGH
    0.08
    ÑĢак
    0.08
    ä¸įçĽ¸ä¿¡
    0.08
    ä¸ĭéĿ¢æĪij们
    0.08
    Activations Density 0.078%

    No Known Activations