© 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. 11776
    Prev
    Next
    INDEX
    Explanations

    footballer

    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
    odian
    -0.20
    _patterns
    -0.19
    两类
    -0.19
    è¿ĩåħ³
    -0.18
    åīij
    -0.18
    iphers
    -0.18
    tsky
    -0.18
    _nbr
    -0.17
    asers
    -0.17
    å½ĸ
    -0.17
    POSITIVE LOGITS
    åŀ¦
    0.20
    myp
    0.20
    å±¥
    0.19
    _RUNNING
    0.19
    ŃIJ
    0.19
    çļĦ巨大
    0.18
    çłĶ究çĶŁ
    0.18
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.18
    个ä½ĵ
    0.18
    ä¾Ŀæ³ķ追究
    0.18
    Activations Density 0.108%

    No Known Activations