© 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. 49823
    Prev
    Next
    INDEX
    Explanations

    league, tournament, championship, win

    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
    è£ħå¤ĩåĪ¶éĢł
    -0.10
    缤
    -0.09
    onio
    -0.09
    æ¯ıä½į
    -0.09
    æĻĮ
    -0.09
    æħİ
    -0.09
    æħij
    -0.08
    éļıå¤Ħ
    -0.08
    è¬Ľ
    -0.08
    çļĦ认è¯Ĩ
    -0.08
    POSITIVE LOGITS
    å·ŀ
    0.09
    å¤©åĽ½
    0.08
    thane
    0.08
    å·ŀå¸Ĥ
    0.08
    ä¼
    0.08
    otos
    0.08
    ãģĤãģ£ãģ¦
    0.08
     Elem
    0.08
    Haz
    0.08
    çŃī级
    0.08
    Activations Density 0.065%

    No Known Activations