© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    import/imported related words

    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
    å¬
    -0.10
    èĤ¡æ°ij
    -0.10
    ÑĪÑĥ
    -0.09
     ÃŃch
    -0.09
    ðŁijĩ
    -0.09
     nale
    -0.08
    çªĪ
    -0.08
    ç«ĭæĸ¹
    -0.08
    :variables
    -0.08
    лов
    -0.08
    POSITIVE LOGITS
    è¿ĽæĿ¥
    0.17
    (import
    0.11
    è¿ĩæĿ¥
    0.10
    /export
    0.10
    è¿Ľåı£
    0.10
     into
    0.10
     importing
    0.09
    éģİä¾Ĩ
    0.09
    导åħ¥
    0.09
    antly
    0.09
    Activations Density 0.069%

    No Known Activations