© 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. 49756
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
    ×ķת
    -0.09
    åĽ¢
    -0.08
    ric
    -0.08
    å¾Ī强
    -0.08
    icol
    -0.08
    礼
    -0.08
    çIJħ
    -0.08
    ONY
    -0.08
    åİ»åĮ»éĻ¢
    -0.08
    èĬĤæ°´
    -0.08
    POSITIVE LOGITS
    æľī幸
    0.09
    nob
    0.09
    (paren
    0.08
    çĻ½é©¬
    0.08
    大å®Ĺ
    0.08
    ä¸įä¸Ĭ
    0.08
    utom
    0.08
    æĹĦ
    0.08
    æĸ°åĨłçĸ«æĥħ
    0.08
    æ§İ
    0.08
    Activations Density 0.133%

    No Known Activations