© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37930
    Prev
    Next
    INDEX
    Explanations

    film, book, or game series

    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
    åIJIJ
    -0.10
    ç«Ń
    -0.10
    çļĦè®°å¿Ĩ
    -0.09
    çݯèĬĤ
    -0.08
    ç¼ł
    -0.08
    éħį
    -0.08
    è¿Ľè¡Įåħ¨éĿ¢
    -0.08
    ayar
    -0.08
    妻
    -0.08
    çĸ¾
    -0.08
    POSITIVE LOGITS
    ç³»åĪĹ
    0.14
    ãĤ·ãĥªãĥ¼ãĤº
    0.13
     series
    0.11
    ç³»åĪĹ产åĵģ
    0.11
    ä¸Ģ缴
    0.10
     ÑģеÑĢии
    0.09
    ä¸ĢçĽ´æ²¡æľī
    0.09
    éĻĨç»Ń
    0.09
    .series
    0.09
     serie
    0.09
    Activations Density 0.201%

    No Known Activations