© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51891
    Prev
    Next
    INDEX
    Explanations

    `@rem`

    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
    人士
    -0.11
     überh
    -0.09
    履约
    -0.09
    æ¸ł
    -0.09
    aeda
    -0.09
     wards
    -0.09
     Rudd
    -0.09
    æµ°
    -0.09
    çݯå¢ĥä¿ĿæĬ¤
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    POSITIVE LOGITS
    rm
    0.08
    å´§
    0.07
    è¿Ļæł·çļĦè¯Ŀ
    0.07
    sted
    0.07
    alm
    0.07
    èĻ±
    0.07
    ç»Ļ大家
    0.07
    伦
    0.07
    apan
    0.07
     sob
    0.07
    Activations Density 0.311%

    No Known Activations