© 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. 16834
    Prev
    Next
    INDEX
    Explanations

    turn or back

    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
    çĻ½é©¬
    -0.10
    è£ħ
    -0.09
    çŁ¥éģĵäºĨ
    -0.09
    à¸Ľà¸£à¸°à¸Ĭา
    -0.08
    课å¤ĸ
    -0.08
     EPS
    -0.08
    çŁ¥éģĵ
    -0.08
    Globals
    -0.08
    uario
    -0.08
    AFP
    -0.08
    POSITIVE LOGITS
    eni
    0.11
    éĢĢåĽŀ
    0.10
    åĭ¾
    0.10
    æŃ¢
    0.10
    åģľçķĻ
    0.10
    åĽŀåİ»
    0.09
    åīįæĻ¯
    0.09
    è¿Ķ
    0.09
    åĽŀä¾Ĩ
    0.09
    è¿ĺåĮħæĭ¬
    0.09
    Activations Density 0.025%

    No Known Activations