© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15043
    Prev
    Next
    INDEX
    Explanations

    sesame and jasmine plants

    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
    èİĵ
    -0.17
    xffffffff
    -0.17
     Boss
    -0.17
    iful
    -0.17
    ulet
    -0.16
    èĦ¯
    -0.16
     Gast
    -0.16
     quê
    -0.16
    é¹ŀ
    -0.16
     lion
    -0.15
    POSITIVE LOGITS
    èĬĿ麻
    0.27
     seeds
    0.21
    izedName
    0.21
    æĴŃ
    0.20
    ç§įåŃIJ
    0.20
    female
    0.19
    äºĶè¡Į
    0.19
    å¢Ģ
    0.19
    dana
    0.19
    大è±Ĩ
    0.19
    Activations Density 0.003%

    No Known Activations