© 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. 10749
    Prev
    Next
    INDEX
    Explanations

    nail polish

    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
    èĦijè¢ĭ
    -0.22
     Winds
    -0.22
     Soap
    -0.21
    åĨĹ
    -0.20
    æ±Łæ·®
    -0.19
     choke
    -0.19
    æĮĩæĮ¥
    -0.19
    é¹ŀ
    -0.19
    itur
    -0.19
    è°ĥ
    -0.19
    POSITIVE LOGITS
    æĮĩçĶ²
    0.28
    гаÑĢ
    0.21
     nail
    0.20
    ç»ĨåĪĻ
    0.20
    inals
    0.20
    ÑĤвеÑĢд
    0.20
    è·ĸ
    0.20
    家åĬ¡
    0.19
    digits
    0.19
    ermen
    0.19
    Activations Density 0.023%

    No Known Activations