© 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. 57130
    Prev
    Next
    INDEX
    Explanations

    ambiguity and uncertainty

    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
    anse
    -0.08
     excuse
    -0.08
     CET
    -0.08
    nez
    -0.08
    éªŀ
    -0.08
    iets
    -0.08
    rong
    -0.08
    sv
    -0.08
    Ñĩен
    -0.08
    .workflow
    -0.07
    POSITIVE LOGITS
    ä¸įæ¸ħ
    0.11
    ä¸įå®ļ
    0.10
    ä¸įæ¸ħæ¥ļ
    0.10
     khÄĥn
    0.09
    æĢ§å¼º
    0.09
    èĥľè´Ł
    0.09
    æĻĭæ±Ł
    0.09
    èµ·ä¼ı
    0.09
    å¾Ĺå¾Ī
    0.09
    尺度
    0.09
    Activations Density 0.041%

    No Known Activations