© 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. 29712
    Prev
    Next
    INDEX
    Explanations

    is a / is the

    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¸īä½įä¸Ģä½ĵ
    -0.08
    è°ĵ
    -0.08
    åĪ°ä½į
    -0.07
    åĴ¸
    -0.07
    åħĥå®Ŀ
    -0.07
     -
    -0.07
    åĪį
    -0.07
    é¦Ĩ
    -0.07
    计
    -0.07
     &
    -0.07
    POSITIVE LOGITS
    大éģĵ
    0.11
    edly
    0.10
    idders
    0.10
    hest
    0.10
    éĩįè¦ģæĮĩ示
    0.10
    á»ĥn
    0.10
    宥
    0.10
    大éħĴåºĹ
    0.09
    å±ĢéĿ¢
    0.09
    OUT
    0.09
    Activations Density 0.180%

    No Known Activations