© 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. 28068
    Prev
    Next
    INDEX
    Explanations

    State associated institutions

    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
    zelf
    -0.09
    éľģ
    -0.09
    çīĪæĿĥæīĢæľī
    -0.08
    æľ¬ç½ijç«Ļ
    -0.08
    ote
    -0.08
    wan
    -0.08
    ä¼łçIJĥ
    -0.08
    æ³Ĭ
    -0.08
    åįģ足
    -0.08
     suffix
    -0.08
    POSITIVE LOGITS
    ÑĢад
    0.10
    ç¯ģ
    0.09
    ilians
    0.09
    dap
    0.09
    ÐĻ
    0.08
    èĨ
    0.08
    FRAME
    0.08
    iegel
    0.08
    wick
    0.08
    ying
    0.08
    Activations Density 0.003%

    No Known Activations