© 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. 13447
    Prev
    Next
    INDEX
    Explanations

    fairs and shows

    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
     strokes
    -0.20
    findFirst
    -0.20
    .Dom
    -0.19
    ç¤ģ
    -0.19
    åĥµ
    -0.19
     stroke
    -0.19
     volley
    -0.18
     Xia
    -0.18
     Exped
    -0.18
    æľĢè¿ij
    -0.18
    POSITIVE LOGITS
    grounds
    0.30
    azine
    0.22
    åĽŃ
    0.21
    åľĥ
    0.21
    åľºåľ°
    0.21
    çļĦæĹ¥åŃIJ
    0.20
    æŀŀ
    0.20
    éĺī
    0.20
    éĥ¨åī¯
    0.20
    ground
    0.20
    Activations Density 0.003%

    No Known Activations