© 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. 48912
    Prev
    Next
    INDEX
    Explanations

    new followed by a noun

    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éĢī
    -0.10
    edImage
    -0.10
    è£Ķ
    -0.09
    墩
    -0.09
    çĩ§
    -0.09
    çĻ»ä¸Ĭ
    -0.08
     entreprene
    -0.08
    æİĮ声
    -0.08
    ullo
    -0.08
    à®±
    -0.08
    POSITIVE LOGITS
    fell
    0.09
    æĸ°ä¸Ģ代
    0.09
    linger
    0.09
    ä¸ĭä¸Ģ代
    0.09
    .rev
    0.08
    ç½ijä¸Ĭ
    0.08
    æł·åŃIJ
    0.08
    ÙģاÙĤ
    0.08
    åı¯è°ĵæĺ¯
    0.08
    iele
    0.08
    Activations Density 0.043%

    No Known Activations