© 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. 39544
    Prev
    Next
    INDEX
    Explanations

    power and transmission

    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
    uez
    -0.11
    uil
    -0.09
    reh
    -0.09
    æĬķæľº
    -0.09
    ç´¯
    -0.09
    ä¸ĢåłĨ
    -0.09
    eme
    -0.09
    è®®äºĭ
    -0.09
     Operating
    -0.09
     Elev
    -0.09
    POSITIVE LOGITS
    æģ©
    0.10
    è¾ĵåĩº
    0.10
     Hind
    0.10
    马åĬĽ
    0.09
    æĻ¶
    0.09
    XE
    0.08
     output
    0.08
    $output
    0.08
    ä¸įå¿ĺ
    0.08
     Kap
    0.08
    Activations Density 0.054%

    No Known Activations