© 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. 57656
    Prev
    Next
    INDEX
    Explanations

    laden, -free, -packed, -driven

    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
    å±±åºĦ
    -0.11
    æĨİ
    -0.10
    _POINTER
    -0.09
    æ·Ģ
    -0.09
    issor
    -0.09
    /releases
    -0.09
    æĬµæĮ¡
    -0.09
    å¿įåıĹ
    -0.08
    æŨ
    -0.08
    -sizing
    -0.08
    POSITIVE LOGITS
    less
    0.11
    丰å¯ĮçļĦ
    0.10
    å¯ĨéĽĨ
    0.09
    äºijéĽĨ
    0.09
    inte
    0.09
    иÑĢован
    0.09
    orient
    0.08
    丰å¯Į
    0.08
    è±IJå¯Į
    0.08
    iless
    0.08
    Activations Density 0.188%

    No Known Activations