© 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. 17979
    Prev
    Next
    INDEX
    Explanations

    nudibranchs or flatworms

    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
    è¯ī
    -0.10
    äºijéĽĨ
    -0.10
    èĭ±æĸĩ
    -0.10
    ç¿Ĭ
    -0.09
    éĺ²æݧ
    -0.09
    è¯ł
    -0.09
    æĬ½åĩº
    -0.09
    æīĵçĿĢ
    -0.09
    æĬ½åıĸ
    -0.09
    解æķ£
    -0.09
    POSITIVE LOGITS
     top
    0.09
    å¤į
    0.09
    uki
    0.08
    åıĮåIJij
    0.08
    横åIJij
    0.08
    ä¸Ģæµģ
    0.08
    _UNS
    0.08
    å¦Ļ
    0.08
    æ½
    0.08
    بات
    0.08
    Activations Density 0.076%

    No Known Activations