© 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. 58652
    Prev
    Next
    INDEX
    Explanations

    to check, determine, or reveal

    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
    绣绣
    -0.10
    éĿ¢åIJij
    -0.10
    åģıåIJij
    -0.09
    ÏĮ
    -0.09
    lap
    -0.09
    zig
    -0.09
    asted
    -0.09
     laps
    -0.08
    renom
    -0.08
    è¿ĻäºĽéĹ®é¢ĺ
    -0.08
    POSITIVE LOGITS
    çľĭçľĭ
    0.17
    æĺ¯åIJ¦æľī
    0.15
    究竣
    0.13
    çľĭä¸Ģçľĭ
    0.13
     whether
    0.12
    æĺ¯åIJ¦
    0.12
    çľĭä»ĸ
    0.12
    çľĭä½ł
    0.12
    æĿ¥çľĭçľĭ
    0.11
    æľī没æľī
    0.10
    Activations Density 0.170%

    No Known Activations