© 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. 33145
    Prev
    Next
    INDEX
    Explanations

    r&b and urban radio genres

    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
    udios
    -0.09
    éļĶçĿĢ
    -0.09
    ç»ıèIJ¥èĮĥåĽ´
    -0.09
    adol
    -0.09
    èĩªè¡Į车
    -0.08
    adic
    -0.08
    èīºæľ¯åĵģ
    -0.08
    à¸Ńà¸Ń
    -0.08
    kos
    -0.08
    ARGE
    -0.08
    POSITIVE LOGITS
    æĭIJ
    0.11
    椹
    0.10
    人士
    0.10
    åIJĬ顶
    0.09
    å¾Īæ·±
    0.09
    eros
    0.09
    ç¼ł
    0.09
    overn
    0.08
    éĶĻè¿ĩ
    0.08
    olk
    0.08
    Activations Density 0.003%

    No Known Activations