© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21620
    Prev
    Next
    INDEX
    Explanations

    prescription glasses and lenses

    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¸Ń央
    -0.11
    ä¸Ńå±±
    -0.10
    pressed
    -0.09
    MMC
    -0.09
    haust
    -0.09
    å¦Ĥå®ŀ
    -0.09
    å·´å·´
    -0.09
    .enum
    -0.09
    arella
    -0.09
    алÑĮн
    -0.09
    POSITIVE LOGITS
    åıĤ
    0.10
    åIJĦæł·
    0.09
    æ¯Ķéĩį
    0.09
    feel
    0.09
    çģµ
    0.08
     Manit
    0.08
    im
    0.08
    èĩ³ä¸Ĭ
    0.08
    å®ĺåı¸
    0.08
    å¨ģåIJį
    0.08
    Activations Density 0.193%

    No Known Activations