© 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. 32819
    Prev
    Next
    INDEX
    Explanations

    Lafayette, Fayetteville, Lamar

    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
    å¤ł
    -0.09
     à¹Ĩ
    -0.09
    å®ŀå®ŀåľ¨åľ¨
    -0.09
    é«®
    -0.09
    迤
    -0.08
    åľ¨æĪijçľĭæĿ¥
    -0.08
    巨头
    -0.08
    linger
    -0.08
    ÑĨов
    -0.08
    端æŃ£
    -0.08
    POSITIVE LOGITS
    onis
    0.10
    ues
    0.09
    utom
    0.08
     flair
    0.08
    å¾ĹçŁ¥
    0.08
    gage
    0.08
     Guar
    0.08
    /Main
    0.08
    ç¬ij声
    0.08
    tec
    0.07
    Activations Density 0.003%

    No Known Activations