© 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. 1793
    Prev
    Next
    INDEX
    Explanations

    TripAdvisor or Brighton

    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
    ouched
    -0.10
    <<<
    -0.10
    ä¸ĸ人
    -0.09
    otec
    -0.09
    raw
    -0.09
     Colleg
    -0.08
    ited
    -0.08
    airo
    -0.08
    年级
    -0.08
    nty
    -0.08
    POSITIVE LOGITS
    æĶĺ
    0.10
     нед
    0.09
    å·²ç»ıæľīäºĨ
    0.09
    çİij
    0.09
    -going
    0.08
    dek
    0.08
    semblies
    0.08
    atomy
    0.08
    ç»ı纬
    0.08
    è´Ŀ壳
    0.08
    Activations Density 0.001%

    No Known Activations