© 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. 23278
    Prev
    Next
    INDEX
    Explanations

    refraction, autorefraction, myopia

    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
    ocz
    -0.10
    ä¸ĭæīĭ
    -0.10
    ä¸Ĭ线
    -0.10
    rv
    -0.09
    åįłçĶ¨
    -0.08
    onica
    -0.08
     вÑĭпÑĥÑģк
    -0.08
    8
    -0.08
    ĸī
    -0.08
    tl
    -0.08
    POSITIVE LOGITS
    inkel
    0.10
    äº¤æĽ¿
    0.09
    篾
    0.09
    庾
    0.09
    éŀŃ
    0.09
     pear
    0.09
    ç
    0.09
    æĬµ
    0.09
     gross
    0.08
     Conce
    0.08
    Activations Density 0.094%

    No Known Activations