© 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. 27784
    Prev
    Next
    INDEX
    Explanations

    percentages often followed by of

    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
    åIJĽåŃIJ
    -0.09
    ç»Ŀ对
    -0.09
    rowse
    -0.09
    ðĿijģ
    -0.09
    åħ
    -0.08
    éĿ¢ç§¯çº¦
    -0.08
    étique
    -0.08
    ÑĤика
    -0.08
    .mit
    -0.08
    isers
    -0.08
    POSITIVE LOGITS
    åı®åĺ±
    0.09
    人群ä¸Ń
    0.09
    ä¸Ģ群人
    0.09
    åıĸ代
    0.09
    iene
    0.08
    ãģĭãģĭãĤĭ
    0.08
     ÑģобÑģÑĤвенно
    0.08
    åIJĦç§įåIJĦæł·
    0.08
    人å¿ĥ
    0.08
    ä¸Ģè·¯ä¸Ĭ
    0.08
    Activations Density 0.089%

    No Known Activations