© 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. 26175
    Prev
    Next
    INDEX
    Explanations

    Versatile Disk

    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
    Negative Logits
    VEN
    -0.10
    æĪIJåIJį
    -0.10
    å¥ı
    -0.09
    åľ¨åħ¨åĽ½
    -0.09
    æŃ¢
    -0.09
    çīĮ
    -0.09
    æĴµ
    -0.09
    venes
    -0.08
    åīįä¸ĸ
    -0.08
    æĬĢ
    -0.08
    POSITIVE LOGITS
    ç¢Ł
    0.12
    å±ħ
    0.11
    èĬ¡
    0.10
    çĽĺ
    0.09
    -Sah
    0.09
    颦
    0.09
    æĻ®éĢļè¯Ŀ
    0.09
    缤
    0.08
    ifr
    0.08
    çģµ
    0.08
    Activations Density 0.124%

    No Known Activations