© 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. 6861
    Prev
    Next
    INDEX
    Explanations

    laser beam, printer, games, control

    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
    nuts
    -0.09
    uration
    -0.09
    æĺ§
    -0.09
    eland
    -0.08
    sert
    -0.08
     trÄĥm
    -0.08
    广æĴŃ
    -0.08
    tent
    -0.08
    sel
    -0.08
    åĸĩåıŃ
    -0.08
    POSITIVE LOGITS
    çİ«
    0.10
    ç©ij
    0.09
    è¿Ļåıªæĺ¯
    0.09
    çŀij
    0.09
    æĪ¿
    0.09
    disk
    0.09
    تÙĪÙĨ
    0.09
    å¥ĩå¼Ĥ
    0.09
     пÑĢиÑĩ
    0.08
    fixture
    0.08
    Activations Density 0.030%

    No Known Activations