© 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. 10820
    Prev
    Next
    INDEX
    Explanations

    Tumblr, fandom, and fanfiction content warnings

    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
    buzz
    -0.23
    妻
    -0.21
    èĢģèĻİ
    -0.21
     nostalg
    -0.21
    annes
    -0.21
     Eagles
    -0.21
    çļĦ妻åŃIJ
    -0.21
    ORIZ
    -0.20
     Automobile
    -0.20
    éķĽ
    -0.20
    POSITIVE LOGITS
     fandom
    0.23
     Tumblr
    0.23
     anime
    0.22
    anime
    0.22
     tumblr
    0.21
    æĿ¥çľĭçľĭåIJ§
    0.21
    ç¤¾åĽ¢
    0.20
     Discord
    0.20
    ä¸ĵå±ŀ
    0.20
    åħħåĢ¼
    0.20
    Activations Density 0.097%

    No Known Activations