© 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. 35878
    Prev
    Next
    INDEX
    Explanations

    dates and time ranges

    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
    èijij
    -0.10
    ç«Łæĺ¯
    -0.09
    ä¿©
    -0.09
    ä¸ĢéĿ¢
    -0.08
    ä¸Ģå¾ĭ
    -0.08
    åħ³æĢĢ
    -0.08
    æ²Ķ
    -0.08
    èĪ¸
    -0.08
    æ¯Ļ
    -0.08
    anko
    -0.08
    POSITIVE LOGITS
    è¿Ļ两个
    0.10
    缸ç»ĵåIJĪ
    0.09
    以åıĬ
    0.09
    å°±æѤ
    0.09
    ãģ¨ãģĦãģ£ãģŁ
    0.09
    è¿Ļ两年
    0.08
    åIJĦèĩªçļĦ
    0.08
    .ascii
    0.08
    _dirty
    0.08
    .advance
    0.08
    Activations Density 0.172%

    No Known Activations