© 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. 23473
    Prev
    Next
    INDEX
    Explanations

    average, usual, normal

    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
    Wrapped
    -0.09
    ä¸įåIJĮäºİ
    -0.09
    нев
    -0.09
    亿ä¸ĩ
    -0.09
    ãģ¾ãģ¾
    -0.09
    ä¸įå®Į
    -0.09
    .MediaType
    -0.09
     ÑĦакÑĤ
    -0.09
    è°Ĵ
    -0.09
    EDIA
    -0.09
    POSITIVE LOGITS
    å¸Ĥåħ¬å®īå±Ģ
    0.08
    OrNull
    0.08
     Hughes
    0.08
     canned
    0.08
     Tracy
    0.08
    -low
    0.07
     Bros
    0.07
    bras
    0.07
    ibr
    0.07
    éĤ£æ¬¡
    0.07
    Activations Density 0.020%

    No Known Activations