© 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. 58940
    Prev
    Next
    INDEX
    Explanations

    keyboard shortcuts

    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
    亲
    -0.09
    ÑĥлÑĮ
    -0.09
    ä¸įåıĺ
    -0.08
    unal
    -0.08
    æľīäºĨ
    -0.08
    éĻµ
    -0.08
    øy
    -0.08
    elihood
    -0.08
    è¾£
    -0.08
    arya
    -0.08
    POSITIVE LOGITS
    å¾Ĥ
    0.09
    EMENT
    0.08
    .Link
    0.08
    èµ°åĩºæĿ¥
    0.08
    éģĦ
    0.08
    season
    0.08
    getParameter
    0.08
    ãĤīãģĦ
    0.08
    ãģİ
    0.08
    åħ¥ãĤĮ
    0.08
    Activations Density 0.152%

    No Known Activations