© 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. 53733
    Prev
    Next
    INDEX
    Explanations

    Marine Corps

    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
    anine
    -0.09
    害
    -0.08
    çIJĨå·¥
    -0.08
    rite
    -0.08
    kart
    -0.08
    hog
    -0.08
    èĤ²
    -0.08
    _CHIP
    -0.08
    à¦
    -0.08
    ctp
    -0.08
    POSITIVE LOGITS
    æĿ·
    0.10
    顽强
    0.09
    å¼ıçļĦ
    0.09
    ä¼łæŁĵ
    0.09
    人家
    0.09
    éıĸ
    0.09
     Cannon
    0.09
    å¾Ĥ
    0.08
    icon
    0.08
     Corps
    0.08
    Activations Density 0.010%

    No Known Activations