© 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. 34972
    Prev
    Next
    INDEX
    Explanations

    Abbey

    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
    sat
    -0.09
    ually
    -0.09
     же
    -0.09
    ä¸įä¸Ĭ
    -0.08
    ä¹İ
    -0.08
    wel
    -0.08
    å¤ļåľ°
    -0.08
    éĶ¦æłĩèµĽ
    -0.08
    usta
    -0.08
    ä¼ļ对
    -0.08
    POSITIVE LOGITS
     hè
    0.10
    quarters
    0.10
    CTS
    0.09
    kos
    0.09
    饯
    0.09
    ги
    0.09
     sẵn
    0.09
    ritt
    0.09
    FLT
    0.09
    rror
    0.09
    Activations Density 0.003%

    No Known Activations