© 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. 63087
    Prev
    Next
    INDEX
    Explanations

    Hillary Clinton

    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
    ë¥ł
    -0.11
    éľĸ
    -0.09
    ä¸ĬæĬ¥
    -0.09
    itive
    -0.09
    æĻ¨æĬ¥
    -0.09
    el
    -0.09
    绶
    -0.08
    ย
    -0.08
    é»ĺå¥ij
    -0.08
    ernaut
    -0.08
    POSITIVE LOGITS
    enko
    0.10
    ondon
    0.10
    iona
    0.10
    YPE
    0.10
    odont
    0.09
    ÑĥÑĪ
    0.09
    icide
    0.09
    .variant
    0.09
    panic
    0.09
    usk
    0.09
    Activations Density 0.017%

    No Known Activations