© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29781
    Prev
    Next
    INDEX
    Explanations

    against team names

    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
    /g
    -0.09
    ug
    -0.08
     cracking
    -0.08
    itary
    -0.08
     Supported
    -0.08
    1
    -0.07
    æĹ¥å¸¸
    -0.07
    åĬ©éķ¿
    -0.07
    ä¸ĬçıŃæĹı
    -0.07
    æĢİ
    -0.07
    POSITIVE LOGITS
    ç«ŀäºī对æīĭ
    0.13
    æĮijè¡ħ
    0.10
    /respond
    0.10
    对æīĭ
    0.10
    顽
    0.10
     ÑĤоÑĢ
    0.10
    åĬ¬
    0.09
    æĻ®
    0.09
    _TRUNC
    0.09
     nghè
    0.09
    Activations Density 0.020%

    No Known Activations