© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    they followed by a verb

    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
    æ¶ĤæĬ¹
    -0.12
    ä¸İåħ¶ä»ĸ
    -0.10
    æł¹æį®èĩªå·±
    -0.10
    å¼ĢæĿ¥
    -0.09
    两级
    -0.09
    ä¸įåı¯æĪĸ缺
    -0.09
    亲æīĭ
    -0.09
    ä¸įçĶ¨æĭħå¿ĥ
    -0.09
    lining
    -0.09
    åķľ
    -0.09
    POSITIVE LOGITS
    æIJŀ
    0.10
    è¾Ł
    0.09
    åı«æĪij
    0.09
    .union
    0.09
    ehr
    0.08
    .Require
    0.08
    esen
    0.08
    apas
    0.08
    VRT
    0.08
    union
    0.08
    Activations Density 0.079%

    No Known Activations