© 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. 57581
    Prev
    Next
    INDEX
    Explanations

    DISCLAIMER followed by colon

    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¯ĨéĽĨ
    -0.09
    uated
    -0.09
    迸
    -0.09
    /sm
    -0.09
    ronic
    -0.09
    æĤĴ
    -0.08
    çIJ¢
    -0.08
    köp
    -0.08
    erness
    -0.08
    åĿĢ
    -0.08
    POSITIVE LOGITS
    ably
    0.11
    æľ¬ç½ijç«Ļ
    0.11
    éd
    0.10
    ather
    0.10
    責任
    0.09
    edis
    0.09
    è¿ĻéĩĮæĺ¯
    0.09
    æľŁåĨħ
    0.09
     Hog
    0.09
    说æĺ¯
    0.09
    Activations Density 0.035%

    No Known Activations