© 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. 14042
    Prev
    Next
    INDEX
    Explanations

    rock music

    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
    uent
    -0.21
    -Agent
    -0.19
    åľ¨çݩ家ä¸Ń
    -0.18
    edi
    -0.18
    charAt
    -0.18
    лага
    -0.18
    é¹Ń
    -0.18
    åįķèģĮä¸ļ
    -0.17
    éĻĦè¿ij
    -0.17
     pornos
    -0.17
    POSITIVE LOGITS
    æĹ¶ä»£çļĦ
    0.24
    åı²ä¸Ĭ
    0.23
    æĹ¶ä»£
    0.23
    大éģĵ
    0.20
    çĻ¾å¼º
    0.20
    æĥħæĢĢ
    0.19
     heart
    0.19
    年代
    0.19
    style
    0.18
    åIJ¯èĴĻ
    0.18
    Activations Density 0.019%

    No Known Activations