© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 957
    Prev
    Next
    INDEX
    Explanations

    qualities of being or outcome

    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
    æ¼Ķåıĺ
    -0.10
    æĨĶ
    -0.09
    æ¹
    -0.08
    èĢĮåĩº
    -0.08
    .metamodel
    -0.08
    羣æŃ£
    -0.08
    说å¾Ĺ
    -0.08
    深深
    -0.08
    ä¸īå¹´
    -0.08
    ixo
    -0.08
    POSITIVE LOGITS
    à¹ĥà¸Ļà¸ģาร
    0.14
    åľ°çľĭçĿĢ
    0.10
    æīĭä¸ŃçļĦ
    0.09
    åĭĭ
    0.09
    å¦Ĥæľīä¾µæĿĥ
    0.09
     дол
    0.09
    è¿Ļæĸ¹éĿ¢
    0.09
    inel
    0.08
    æĬĬè¿ĻäºĽ
    0.08
    etine
    0.08
    Activations Density 0.034%

    No Known Activations