© 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. 60551
    Prev
    Next
    INDEX
    Explanations

    technology, staff, tutoring, funding, development, visits

    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
    ä¼łæİĪ
    -0.10
     pu
    -0.10
    毫æĹł
    -0.10
     вÑĭпÑĥÑģк
    -0.09
    çī¹æ´¾
    -0.09
    é«ĺçŃīéĻ¢æł¡
    -0.09
    èĥª
    -0.09
    æ±²
    -0.09
    红éħĴ
    -0.09
    åĥ§
    -0.09
    POSITIVE LOGITS
    olk
    0.09
    loth
    0.08
    黯
    0.08
    çľĩ
    0.08
    ä½ľåĩºäºĨ
    0.08
    Ø·ÙĪÙĦ
    0.08
    .jasper
    0.08
    óg
    0.08
    åIJįçīĩ
    0.08
    éĹªçĶµ
    0.08
    Activations Density 0.047%

    No Known Activations