© 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. 29888
    Prev
    Next
    INDEX
    Explanations

    keyword related phrases

    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
    éĿ©æĸ°
    -0.09
    fully
    -0.09
    heet
    -0.09
    batim
    -0.09
    ees
    -0.09
    éģı
    -0.09
    western
    -0.09
    born
    -0.08
    KeyName
    -0.08
    orted
    -0.08
    POSITIVE LOGITS
    ìĸ¼
    0.12
    IEL
    0.09
    äºĭå®ľ
    0.09
    üh
    0.09
    澡
    0.08
    æݧèĤ¡éĽĨåĽ¢
    0.08
    iel
    0.08
    æĵį
    0.08
    alog
    0.08
    ìĺ¥
    0.08
    Activations Density 0.006%

    No Known Activations