© 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. 61363
    Prev
    Next
    INDEX
    Explanations

    pre- words and level comparison

    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
    æĨ¨
    -0.09
    仨
    -0.09
     Ñĥзн
    -0.08
    è·£
    -0.08
    kö
    -0.08
    ocl
    -0.08
    æĮĩåIJij
    -0.08
    æ¦ľ
    -0.08
    ä¸ĢæīĢ
    -0.08
    ÑĨеп
    -0.08
    POSITIVE LOGITS
     levels
    0.13
    æ°´å¹³
    0.11
    levels
    0.11
     ÑĥÑĢовнÑı
    0.10
     Levels
    0.10
    å·¡èĪª
    0.09
     ÑĥÑĢов
    0.09
     level
    0.09
    juan
    0.09
    agher
    0.09
    Activations Density 0.050%

    No Known Activations