© 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. 19076
    Prev
    Next
    INDEX
    Explanations

    Mc names and suffixes

    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
    enko
    -0.10
     оÑĤзÑĭв
    -0.09
    annis
    -0.09
    .uc
    -0.09
    饮æĸĻ
    -0.09
    æŃ»åİ»
    -0.08
    cid
    -0.08
    UA
    -0.08
    æĹħ游å±Ģ
    -0.08
    uco
    -0.08
    POSITIVE LOGITS
    ï¸
    0.10
    ude
    0.08
    声éģĵ
    0.08
    ç§ijåĪĽæĿ¿
    0.08
    inely
    0.08
     Strauss
    0.08
    ä¿Ŀå®ī
    0.08
    çļĭ
    0.08
     rec
    0.08
    (vc
    0.08
    Activations Density 0.002%

    No Known Activations