© 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. 14291
    Prev
    Next
    INDEX
    Explanations

    racing circuits and locations

    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
    desk
    -0.19
    éĴ²
    -0.19
     pops
    -0.19
    ipop
    -0.18
    ucher
    -0.18
    ually
    -0.18
     Desk
    -0.18
    åĿIJåľ¨
    -0.17
    è¡Ģ
    -0.17
     Randolph
    -0.17
    POSITIVE LOGITS
    åıįèħIJåĢ¡å»ī
    0.22
    è¿İæĿ¥
    0.22
    æľĢåIJİä¸Ģ次
    0.20
    æľ¬æ¬¡
    0.20
    setDescription
    0.20
    éĿĴå±±
    0.20
    åħ¨åŁŁ
    0.19
    éĺ´å½±
    0.19
    宣è¨Ģ
    0.19
     Resort
    0.19
    Activations Density 0.021%

    No Known Activations