© 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. 57925
    Prev
    Next
    INDEX
    Explanations

    aside, apart

    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
    æĦıåIJij
    -0.09
    zig
    -0.09
    ìį¨
    -0.09
    thead
    -0.09
    ician
    -0.09
    ä¸įåľ¨
    -0.09
    ç±į
    -0.09
    asting
    -0.09
    é¬ĵ
    -0.09
    ä»İæł¹æľ¬ä¸Ĭ
    -0.08
    POSITIVE LOGITS
    rum
    0.09
    ØŃر
    0.08
    èŀ³
    0.08
    onia
    0.08
     ÙĦØ°ÙĦÙĥ
    0.08
    abouts
    0.07
     UNIVERS
    0.07
    wards
    0.07
    شت
    0.07
    ä¹ĭ称
    0.07
    Activations Density 0.005%

    No Known Activations