© 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. 4987
    Prev
    Next
    INDEX
    Explanations

    one or each occurrence

    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
    人工
    -0.09
    LEAR
    -0.09
    Invocation
    -0.09
    _procs
    -0.09
     cá»ķ
    -0.09
    .proc
    -0.09
    ITT
    -0.08
    æĿĥ
    -0.08
    ThreadId
    -0.08
    _typeof
    -0.08
    POSITIVE LOGITS
    容纳
    0.11
    éĻIJéĩı
    0.10
    åIJįé¢Ŀ
    0.10
    çļĦç«ŀäºī
    0.09
    ä¸įè¶ħè¿ĩ
    0.09
    ä¸įéĻIJ
    0.09
    æĤ²è§Ĥ
    0.09
    éªĽ
    0.09
    éªij
    0.09
    è¿ĩå¤ļ
    0.09
    Activations Density 0.047%

    No Known Activations