© 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. 53696
    Prev
    Next
    INDEX
    Explanations

    season starter

    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
    ä¸ĭçıŃ
    -0.10
    æĻļé¤IJ
    -0.10
    ç»ĪçĤ¹
    -0.09
    æ¯ķä¸ļåIJİ
    -0.09
    åįĬå¤ľ
    -0.09
    åħ¨éķĩ
    -0.09
    åĪ³
    -0.09
    æĪIJéķ¿ä¸º
    -0.09
    çijĻ
    -0.09
    åIJĥçļĦ
    -0.09
    POSITIVE LOGITS
     Initial
    0.11
    åºıå¹ķ
    0.11
     initial
    0.11
    _fatal
    0.10
    ä¼Ĭå§ĭ
    0.09
    Initial
    0.09
    .launch
    0.09
    帷
    0.09
    çľģå¸Ĥ
    0.09
    .startDate
    0.08
    Activations Density 0.054%

    No Known Activations