© 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. 29737
    Prev
    Next
    INDEX
    Explanations

    discussing terminology and language

    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
    åijĬ
    -0.10
    åģļçļĦäºĭ
    -0.09
    沧
    -0.09
    ä¸Ģ段
    -0.09
    好è¿IJ
    -0.08
    沸
    -0.08
    延伸
    -0.08
    è·¨
    -0.08
    ä¿¡èªī
    -0.08
    éĢģåĩº
    -0.08
    POSITIVE LOGITS
     terminology
    0.12
    æľ¯è¯Ń
    0.12
    æݪ
    0.12
     terms
    0.11
    éĺ±
    0.10
     term
    0.10
    æ¦Ĥ念
    0.10
    terms
    0.10
    /terms
    0.10
    è¿Ļ个è¯į
    0.10
    Activations Density 0.080%

    No Known Activations