© 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. 59117
    Prev
    Next
    INDEX
    Explanations

    deluxe version, duplex scan, debug point

    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
    aris
    -0.10
    èĥ¡åŃIJ
    -0.09
    /or
    -0.09
    åŃļ
    -0.09
     иÑģкÑĥÑģ
    -0.08
    jab
    -0.08
    aras
    -0.08
    åŃ¦å®¶
    -0.08
     proverb
    -0.08
    ÑĢож
    -0.08
    POSITIVE LOGITS
    çīĪ
    0.13
    iliary
    0.12
    æĹłæ¯Ķ
    0.10
    è¿IJåĬ¨ä¼ļ
    0.10
    azÄĥ
    0.09
    æĥħåĨµä¸ĭ
    0.09
    ury
    0.09
    MSC
    0.09
    ubb
    0.09
    ä¸ĢæŃ¥
    0.09
    Activations Density 0.005%

    No Known Activations