© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 18779
    Prev
    Next
    INDEX
    Explanations

    non-conference game, non-league game, non-conference victory, non-league football, non-title fight

    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
    æĩĤäºĭ
    -0.10
    åºľ
    -0.10
    åħ±äº«
    -0.10
    éļ½
    -0.10
    åħģ
    -0.09
    è¯Ĩ
    -0.09
    æĹłæīĢ
    -0.09
    èĢĺ
    -0.09
    wiki
    -0.09
    ä»»æľŁ
    -0.09
    POSITIVE LOGITS
    iro
    0.09
    aign
    0.09
    ductory
    0.09
    -ending
    0.08
    .slide
    0.08
    fan
    0.07
    aking
    0.07
    å¤ĸ
    0.07
    (extra
    0.07
     Knights
    0.07
    Activations Density 0.002%

    No Known Activations