© 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. 1505
    Prev
    Next
    INDEX
    Explanations

    cut away, cut into, cut off

    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
    é¡·
    -0.11
    éħIJ
    -0.09
    æݸ
    -0.09
    olie
    -0.09
     Kash
    -0.09
     Lump
    -0.09
    кам
    -0.09
     '::
    -0.09
    succ
    -0.09
    errer
    -0.09
    POSITIVE LOGITS
    é¢łè¦Ĩ
    0.11
    åħ¨éĿ¢æıIJåįĩ
    0.09
    ç«Ļç«ĭ
    0.08
    å¤±æľĽ
    0.08
     shape
    0.08
    ç¯ĩ
    0.08
    æĢĢçĿĢ
    0.08
    åij¨æģ©æĿ¥
    0.08
    ä¸ĭäºĨ
    0.08
    åĿį
    0.08
    Activations Density 0.179%

    No Known Activations