© 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. 57431
    Prev
    Next
    INDEX
    Explanations

    finding clues or insights

    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
    æ¯ıä¸Ģ天
    -0.09
    èĵģ
    -0.09
    ä¸įç®¡ä½ł
    -0.09
    ä»ĸ们éĥ½
    -0.09
    èīĩ
    -0.08
    è°Ģ
    -0.08
    ä¸įåľ¨ä¹İ
    -0.08
    ä¸įä¹ħ
    -0.08
    asil
    -0.08
     Reporter
    -0.08
    POSITIVE LOGITS
     clue
    0.17
     clues
    0.17
    线索
    0.16
    èĽĽ
    0.13
    æľīæīĢ帮åĬ©
    0.11
     cue
    0.10
     hint
    0.10
    çªģçł´åı£
    0.10
     hints
    0.10
    æĸ¹åIJij
    0.10
    Activations Density 0.134%

    No Known Activations