© 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. 23527
    Prev
    Next
    INDEX
    Explanations

    Rev or Hon titles

    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
    ichten
    -0.10
    è¿Ļ件
    -0.09
    èĬ±æľµ
    -0.09
    è¾Ń
    -0.09
    agna
    -0.09
    åĴ¬
    -0.09
     Telegram
    -0.08
    è¹Ĵ
    -0.08
    篷
    -0.08
    京津
    -0.08
    POSITIVE LOGITS
    /moment
    0.10
    们
    0.09
    formats
    0.09
    ãĥĭãĥĥãĤ¯
    0.09
    oger
    0.09
    _hw
    0.09
    ematic
    0.08
    cline
    0.08
    为é¦ĸ
    0.08
    à¸Ĺà¸Ńà¸Ķ
    0.08
    Activations Density 0.002%

    No Known Activations