© 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. 18721
    Prev
    Next
    INDEX
    Explanations

    autocomplete suggestions

    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
    verbosity
    -0.09
    &view
    -0.08
    _GENERIC
    -0.08
    æĿ¿åĿĹ
    -0.08
     Flux
    -0.08
     verbosity
    -0.08
    éĤ£ä¸Ģ天
    -0.08
    æļĦ
    -0.08
    ç¼ł
    -0.08
    tors
    -0.08
    POSITIVE LOGITS
    èģĶæĥ³
    0.11
    .AutoComplete
    0.11
     autocomplete
    0.10
    autocomplete
    0.10
    é¢ĦæĬ¥
    0.09
    ahead
    0.09
     suggestions
    0.09
    èĹ¿
    0.09
    Suggestions
    0.09
    羿
    0.09
    Activations Density 0.178%

    No Known Activations