© 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. 61483
    Prev
    Next
    INDEX
    Explanations

    numbers following strings

    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
    ä¸ĸçķĮåIJĦåĽ½
    -0.09
    ä¼Ĺ人
    -0.09
    举æŃ¢
    -0.08
    stakes
    -0.08
    å¡ij
    -0.08
    ined
    -0.08
    æ·Ŀ
    -0.08
    á»ijt
    -0.08
    sten
    -0.08
    æľ¯åIJİ
    -0.08
    POSITIVE LOGITS
    ذر
    0.09
    翳
    0.08
    urable
    0.08
    妨
    0.08
     reflexivity
    0.08
    -rock
    0.08
    å¹»
    0.08
    èĸĦå¼±
    0.08
    åħ¥ãĤĬ
    0.08
    اس
    0.08
    Activations Density 0.137%

    No Known Activations