© 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. 3109
    Prev
    Next
    INDEX
    Explanations

    such a

    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¸Ģå®ļçļĦ
    -0.12
    æľĢå¤ļçļĦ
    -0.10
    å¾Ī大
    -0.10
    ä¸ĵä¸ļæĬĢæľ¯
    -0.09
    æľĢä½³
    -0.09
    å¾Ī大çļĦ
    -0.09
    ä¸Ģå®ļ
    -0.09
    åIJĦç§į
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
     jug
    -0.08
    POSITIVE LOGITS
    iled
    0.11
     اÙĦØŃاÙĦ
    0.11
    heid
    0.11
    åĽŀäºĭ
    0.11
    -called
    0.10
    éĻ¤æѤ
    0.10
    /from
    0.10
    éĩįå·¥
    0.10
    FRING
    0.10
    portun
    0.10
    Activations Density 0.013%

    No Known Activations