© 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. 13016
    Prev
    Next
    INDEX
    Explanations

    school and education institutions

    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
    笳
    -0.19
    觥
    -0.18
    æ¬ł
    -0.18
    为æ°ij
    -0.18
    пÑĥÑģка
    -0.18
    /code
    -0.18
    enate
    -0.17
     Leisure
    -0.17
    润æ»ij
    -0.17
    -wide
    -0.17
    POSITIVE LOGITS
    ä½ĵç³»
    0.21
    åħ¨å¥Ĺ
    0.20
     local
    0.20
    åĮº
    0.19
    åįĢ
    0.19
    tek
    0.19
     District
    0.19
    ABL
    0.19
     ÑħаÑĢакÑĤеÑĢиÑģÑĤик
    0.19
    沿éĢĶ
    0.18
    Activations Density 0.025%

    No Known Activations