© 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. 49828
    Prev
    Next
    INDEX
    Explanations

    makes it

    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
    åľ¨è¿ĻéĩĮ
    -0.10
    åľ¨ä»ĸçļĦ
    -0.09
    arto
    -0.09
    gran
    -0.09
    å±Ģéķ¿
    -0.09
    inq
    -0.09
    .Loader
    -0.08
    è¢ĸ
    -0.08
    éĶ£
    -0.08
    лан
    -0.08
    POSITIVE LOGITS
    æľīå¿ħè¦ģ
    0.10
    å¾Īéļ¾
    0.10
    äººæł¼
    0.10
    æĹłæ³ķ
    0.10
    éļ¾ä»¥
    0.09
    没åĬŀæ³ķ
    0.09
    ä¸įåı¯èĥ½
    0.09
    äºĨä¸Ģåı¥
    0.09
    ODO
    0.09
    ç¿Į
    0.09
    Activations Density 0.034%

    No Known Activations