© 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. 56801
    Prev
    Next
    INDEX
    Explanations

    in every way

    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
    èĬ±
    -0.10
    igit
    -0.10
    gef
    -0.09
    ÎĨ
    -0.08
    etur
    -0.08
    æĭ±
    -0.08
    shaw
    -0.08
    elan
    -0.08
     Clarence
    -0.08
    .twig
    -0.08
    POSITIVE LOGITS
    åIJĦ个æĸ¹éĿ¢
    0.17
    åIJĦæĸ¹éĿ¢
    0.14
     aspects
    0.13
    ä¸ī个æĸ¹éĿ¢
    0.13
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.12
    好åĩłä¸ª
    0.12
     aspect
    0.11
    æĸ¹éĿ¢
    0.11
    å¤ļ个
    0.11
    åĩłä¸ª
    0.10
    Activations Density 0.053%

    No Known Activations