© 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. 38897
    Prev
    Next
    INDEX
    Explanations

    SSL implementation encryption protection

    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
    ouver
    -0.09
    ial
    -0.09
    esp
    -0.09
    hausen
    -0.08
     Nuggets
    -0.08
    媳å¦ĩ
    -0.08
    ÑĪиÑĢ
    -0.08
    amarin
    -0.08
    溢
    -0.08
    lot
    -0.08
    POSITIVE LOGITS
    车éģĵ
    0.09
    车å±ķ
    0.08
    ØŃÙĬ
    0.08
    æľ¬æĬ¥è®°èĢħ
    0.08
    iced
    0.08
    åģİ
    0.08
    éŃĶçİĭ
    0.08
    æĬ±
    0.08
    leveland
    0.08
    _forum
    0.08
    Activations Density 0.048%

    No Known Activations