© 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. 975
    Prev
    Next
    INDEX
    Explanations

    encoded character sequences

    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
     ÑĢож
    -0.09
     Ñĥже
    -0.09
    quo
    -0.09
    ovich
    -0.09
    æĪij没æľī
    -0.09
     ниÑĩ
    -0.09
    CUS
    -0.08
    è¡Ķ
    -0.08
     ÑĢаÑģпÑĢ
    -0.08
    åĪĨåĪ«æĺ¯
    -0.08
    POSITIVE LOGITS
    ä¸Ģç§į
    0.10
    ä¸ªå·¥ä½ľ
    0.09
    æĸ°ä¸Ģ代
    0.09
    &nbsp
    0.09
    ä¸į失
    0.09
    人大代表
    0.08
    áŀ
    0.08
    ä¸Ģ種
    0.08
    äºĨä¸ĢäºĽ
    0.08
    åħ¶æīĢ
    0.08
    Activations Density 0.152%

    No Known Activations