© 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. 51897
    Prev
    Next
    INDEX
    Explanations

    following `In`

    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
    被认为
    -0.09
    ÑĮ
    -0.09
    å°»
    -0.09
    åĻ¢
    -0.08
    ãģ£ãģ¨
    -0.08
    èĵĦ
    -0.08
    ä¹ĭç¾İ
    -0.08
    濯
    -0.08
    åĮı
    -0.08
    åŃij
    -0.08
    POSITIVE LOGITS
    ç»Ļ大家
    0.10
    dera
    0.09
    æĦŁæĤŁ
    0.09
    hé
    0.09
    æļĩ
    0.09
    ÙħÙĤ
    0.08
    åŀĨ
    0.08
    å°ıç¼ĸ
    0.08
    å°ıä¼Ļ伴们
    0.08
    Bes
    0.08
    Activations Density 0.058%

    No Known Activations