© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3059
    Prev
    Next
    INDEX
    Explanations

    discipline and structured upbringing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    .commons
    -0.23
    èķĪ
    -0.23
    渺
    -0.22
    afil
    -0.21
    Ëļ
    -0.21
    vern
    -0.21
     bump
    -0.20
     hạt
    -0.20
    plits
    -0.20
     Ñĥника
    -0.20
    POSITIVE LOGITS
     disciplined
    0.36
    约æĿŁ
    0.35
     discipline
    0.35
    纪å¾ĭ
    0.34
    ä½ľæģ¯
    0.33
    è§Ħ磩
    0.32
     imposed
    0.31
    è®Ńç»ĥ
    0.28
    èĬĤå¥ı
    0.28
    管çIJĨåĴĮ
    0.27
    Activations Density 0.009%

    No Known Activations