© 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. 39867
    Prev
    Next
    INDEX
    Explanations

    events preceding names

    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
    æĹħé¦Ĩ
    -0.10
    åģ¥èº«æĪ¿
    -0.10
    quir
    -0.09
    太é«ĺ
    -0.09
    orrent
    -0.09
    èĢķ
    -0.09
    æŀ·
    -0.09
    å¤Ļ
    -0.08
    -inner
    -0.08
    é¢Ŀ头
    -0.08
    POSITIVE LOGITS
    夹
    0.10
     sold
    0.09
    iew
    0.09
    çļĦåĪ°æĿ¥
    0.08
    ender
    0.08
    çĶ·å¥³
    0.08
    idget
    0.08
    ä¸ĵ家åѦèĢħ
    0.08
     Skeleton
    0.08
    å¦ĩ
    0.08
    Activations Density 0.089%

    No Known Activations