© 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. 58708
    Prev
    Next
    INDEX
    Explanations

    obtain it

    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
    adesh
    -0.11
    éĬ·
    -0.10
    bis
    -0.10
    epad
    -0.10
    cheid
    -0.09
    ysz
    -0.09
    èĨ¨èĥĢ
    -0.09
    秣
    -0.09
    lain
    -0.09
     маÑĤеÑĢиалов
    -0.09
    POSITIVE LOGITS
    Sony
    0.08
     Trem
    0.08
    ä¼ŀ
    0.08
    åįĹæµ·
    0.08
    é£İæ³¢
    0.08
    åıĸè¯ģ
    0.07
    olumbia
    0.07
     Sco
    0.07
     Pell
    0.07
     dar
    0.07
    Activations Density 0.349%

    No Known Activations