© 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. 55709
    Prev
    Next
    INDEX
    Explanations

    headache

    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
    wer
    -0.11
    hood
    -0.10
    wers
    -0.10
    tle
    -0.09
    aneously
    -0.09
    ALES
    -0.09
    æ°Ķæģ¯
    -0.09
    asant
    -0.08
    athe
    -0.08
    mouth
    -0.08
    POSITIVE LOGITS
    ä¸įå·²
    0.10
    ä¸ĸ人
    0.09
    ometer
    0.09
    绪
    0.09
     latter
    0.09
    oire
    0.08
    aben
    0.08
    å¾Ģäºĭ
    0.08
    extras
    0.08
    èĥ¥
    0.08
    Activations Density 0.006%

    No Known Activations