© 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. 18424
    Prev
    Next
    INDEX
    Explanations

    for each or every

    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
    .Operator
    -0.10
    ILI
    -0.10
    anus
    -0.10
    ToDevice
    -0.09
    ä¸ĭåįĬ
    -0.09
    对æĪijæĿ¥è¯´
    -0.09
    elah
    -0.09
    steller
    -0.09
    æĢİä¹Īæł·
    -0.08
    åľ¨ä»Ĭå¹´
    -0.08
    POSITIVE LOGITS
    aget
    0.08
    vents
    0.08
    DOMNode
    0.08
    ä¸ĢäºĮ
    0.08
     piv
    0.08
    éĴ±
    0.08
    éģį
    0.08
     directing
    0.08
     remembered
    0.08
    vo
    0.08
    Activations Density 0.038%

    No Known Activations