© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53141
    Prev
    Next
    INDEX
    Explanations

    Microsoft products and software

    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
    åŃIJéĩĮ
    -0.10
    ä¸Ńåħ±
    -0.09
    onn
    -0.09
    æ°ijå¿ĥ
    -0.09
    lords
    -0.09
    红éħĴ
    -0.09
    ⾯
    -0.09
    anos
    -0.09
    ictions
    -0.09
    æĦŁäºº
    -0.09
    POSITIVE LOGITS
    å¸ľ
    0.09
    ฯ
    0.09
    zig
    0.09
    ized
    0.09
    .Xna
    0.09
    lect
    0.09
    ften
    0.08
    s
    0.08
    erator
    0.08
    .AspNet
    0.08
    Activations Density 0.042%

    No Known Activations