© 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. 10957
    Prev
    Next
    INDEX
    Explanations

    excited about or to

    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
    大éŨ
    -0.10
    讳
    -0.09
    çİ®
    -0.09
    çłĴ
    -0.09
    .cz
    -0.09
    纱
    -0.09
    .sax
    -0.09
    essler
    -0.08
    anel
    -0.08
    mania
    -0.08
    POSITIVE LOGITS
    ly
    0.11
    iba
    0.10
    ulously
    0.09
    ä¸įå·²
    0.08
    gio
    0.08
    à¹Ĩ
    0.08
    ously
    0.08
    æĪIJ为ä¸ŃåĽ½
    0.08
    iles
    0.08
     pal
    0.08
    Activations Density 0.012%

    No Known Activations