© 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. 62150
    Prev
    Next
    INDEX
    Explanations

    Japanese, Serbian, Hungarian, and other languages

    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
    æ²½
    -0.10
    ä¸ĢæĿ¡
    -0.09
    çĿļ
    -0.09
    åįģæĿ¡
    -0.09
    ffen
    -0.09
    ä¸Ģæ¢Ŀ
    -0.09
    ä¸īæĿ¡
    -0.08
    çĽ¼
    -0.08
    INCT
    -0.08
    amac
    -0.08
    POSITIVE LOGITS
    ifu
    0.09
    æĦı大
    0.09
    oe
    0.09
    æĬ¬èµ·
    0.09
     missile
    0.09
    oplevel
    0.08
     Perr
    0.08
    .expr
    0.08
    é»İ
    0.08
    éĩİ
    0.08
    Activations Density 0.041%

    No Known Activations