© 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. 33191
    Prev
    Next
    INDEX
    Explanations

    NCAA Division I

    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
    ollections
    -0.10
    åı»
    -0.09
    å¹³æŶ
    -0.09
     chamber
    -0.08
    åľ¨æł¡
    -0.08
    æķĻè®Ń
    -0.08
    å°½
    -0.08
    w
    -0.08
    rtle
    -0.07
    æ¦Ķ
    -0.07
    POSITIVE LOGITS
    级
    0.10
    ä¸ŃæľĢ
    0.10
    诸侯
    0.10
    лом
    0.10
    ä¸į容æĺĵ
    0.10
    ASI
    0.10
    éĺµèIJ¥
    0.10
    à¹Ĥล
    0.09
    æľīè¿Ļæł·çļĦ
    0.09
    è¡Ķ
    0.09
    Activations Density 0.149%

    No Known Activations