© 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. 21525
    Prev
    Next
    INDEX
    Explanations

    aisle/isle

    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
    erty
    -0.10
    åľºéĿ¢
    -0.10
    ally
    -0.09
    å¨ij
    -0.09
    nation
    -0.08
    ISTS
    -0.08
    ../../../
    -0.08
    inton
    -0.08
    æ±ł
    -0.08
    ç»ĦåĽ¾
    -0.08
    POSITIVE LOGITS
    ãģ£ãģįãĤĬ
    0.10
    jad
    0.09
    оÑĩнÑĭй
    0.08
    bare
    0.08
    ä¸ī代
    0.08
     تس
    0.08
    缺
    0.08
    cek
    0.08
    _strerror
    0.08
    éªĭ
    0.08
    Activations Density 0.003%

    No Known Activations