© 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. 54176
    Prev
    Next
    INDEX
    Explanations

    suit or fit your

    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
    icum
    -0.11
    纯
    -0.10
    tür
    -0.09
    à¹Ģà¸ī
    -0.09
    åĩ«
    -0.09
    åı¹
    -0.09
    aight
    -0.09
    .Arg
    -0.09
    åĴª
    -0.09
    æ½¢
    -0.09
    POSITIVE LOGITS
    ä¸į失
    0.10
    å®ŀéĻħæĥħåĨµ
    0.10
    æŁIJä¸Ģ
    0.09
    ä¸įæĸŃå¢ŀ强
    0.08
    1
    0.08
    áĥ¥
    0.08
    esc
    0.08
    æ¯ıä¸Ģ
    0.08
    8
    0.08
    æŁIJç§į
    0.08
    Activations Density 0.030%

    No Known Activations