© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 11642
    Prev
    Next
    INDEX
    Explanations

    school performance and learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    æı¡æīĭ
    -0.22
    足迹
    -0.20
    ç¼ĵåĨ²
    -0.19
    æľĢåIJİä¸Ģ次
    -0.19
    ,ev
    -0.19
    大åĬĽ
    -0.19
    èĦIJ
    -0.18
    Naming
    -0.18
    .getExternal
    -0.18
    æĹĹå¸ľ
    -0.18
    POSITIVE LOGITS
    ãĤ¹ãĥĿ
    0.20
     subjects
    0.20
     classroom
    0.19
     frontal
    0.19
     content
    0.19
     learning
    0.19
     catching
    0.19
    á»ĩu
    0.19
     ASTM
    0.19
    Catch
    0.18
    Activations Density 0.035%

    No Known Activations