© 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. 11039
    Prev
    Next
    INDEX
    Explanations

    sports and games

    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
    elmet
    -0.21
    esc
    -0.20
    ä½ĵè´¨
    -0.19
     Ju
    -0.19
     physique
    -0.19
    prod
    -0.18
    æĹ»
    -0.18
     Ign
    -0.18
     Jer
    -0.18
    neau
    -0.18
    POSITIVE LOGITS
    éĹ¯
    0.21
    设æĸ½å»ºè®¾
    0.20
    å¹³æ°ij
    0.20
    èŁł
    0.20
    èĽĩ
    0.20
     Bud
    0.20
    èĶ¬
    0.19
    æĢª
    0.18
    éĻ©
    0.18
    omap
    0.18
    Activations Density 0.001%

    No Known Activations