© 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. 54191
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

    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
    ä¸įæĪIJ
    -0.10
    æł¹æľ¬å°±ä¸į
    -0.09
    æĸĩçī©ä¿ĿæĬ¤
    -0.09
    .Elements
    -0.09
    åĪĩå®ŀ
    -0.09
    ä»Ķ
    -0.09
    åħ´å¥ĭ
    -0.09
     Rune
    -0.09
    åIJĮæŶè¿ĺ
    -0.09
    æĢİä¹Īçľĭ
    -0.09
    POSITIVE LOGITS
     reserved
    0.10
    ä¿ĿçķĻ
    0.09
     reserves
    0.09
    è§ĨåIJ¬
    0.08
    _reserved
    0.08
    _RESERVED
    0.08
     Reserved
    0.08
    å±ŀ
    0.08
    fram
    0.08
    è¿ĻäºĽå¹´
    0.08
    Activations Density 0.021%

    No Known Activations