© 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. 53701
    Prev
    Next
    INDEX
    Explanations

    bracketed content

    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°ijå¿ĥ
    -0.09
    åł¡
    -0.09
    åij¼
    -0.08
    ãĤĤãĤī
    -0.08
    ÑĦе
    -0.08
    å§IJ妹
    -0.08
    人éĥ½
    -0.08
    loth
    -0.08
    pressive
    -0.08
    ä¼ļåĩºçİ°
    -0.08
    POSITIVE LOGITS
    udio
    0.10
    ä¸Ģç§į
    0.10
    !]
    0.09
    +]
    0.09
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ËĮ
    0.09
    ings
    0.09
    ä¸ī个æĸ¹éĿ¢
    0.09
    cem
    0.09
    ä¸Ģ举
    0.09
    Activations Density 0.233%

    No Known Activations