© 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. 62931
    Prev
    Next
    INDEX
    Explanations

    win with promotion or title

    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
    crow
    -0.11
    çĽ
    -0.10
    afil
    -0.09
    å¾Īéķ¿
    -0.09
    Crow
    -0.09
    çł´åĿı
    -0.09
    .fi
    -0.09
    å¾Īæ·±
    -0.09
    ä¹Łä¸įæĥ³
    -0.09
    ADIO
    -0.09
    POSITIVE LOGITS
    åĴĮ个人
    0.13
    èİ·å¾Ĺ
    0.09
    é£ŀè·ĥ
    0.09
    è¯Ħ为
    0.09
    çį²å¾Ĺ
    0.08
    çļĦä¸ĢéĿ¢
    0.08
    İ·
    0.08
    ä¸ĢéĿ¢
    0.08
    åİĨåı²æĢ§
    0.08
    iw
    0.08
    Activations Density 0.048%

    No Known Activations