© 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. 30285
    Prev
    Next
    INDEX
    Explanations

    git diff and patch context

    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
    eti
    -0.10
    .Gr
    -0.09
    裸
    -0.08
    æħĪ
    -0.08
     bunker
    -0.08
    çĿ¿
    -0.08
     BEST
    -0.08
    æĥ³æĥ³
    -0.08
    ='<?
    -0.08
    UME
    -0.08
    POSITIVE LOGITS
     Signed
    0.09
    (patch
    0.09
    çIJ´
    0.09
    æıIJ交
    0.08
    IR
    0.08
     воÑģ
    0.08
    _lineno
    0.08
     signed
    0.08
    agements
    0.08
    è·ĭ
    0.08
    Activations Density 0.215%

    No Known Activations