© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62090
    Prev
    Next
    INDEX
    Explanations

    names starting with Kai

    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
    滥
    -0.09
    æ±ķ
    -0.09
    榴
    -0.09
    çįł
    -0.09
    订éĺħ
    -0.09
    esc
    -0.09
    çīĪæĿĥ
    -0.09
    åĨįä¹Ł
    -0.08
    Edition
    -0.08
    为客æĪ·
    -0.08
    POSITIVE LOGITS
    èĬ
    0.09
    .Cursor
    0.09
     XB
    0.09
    åľ¨åĮĹ京
    0.09
    ocide
    0.08
    åįģåŃĹ
    0.08
    ç¼Ģ
    0.08
    åľ¨äº¬
    0.08
    raph
    0.08
     hoop
    0.08
    Activations Density 0.042%

    No Known Activations