© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46208
    Prev
    Next
    INDEX
    Explanations

    prostitute, vulgar, ugly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıªåı¯æĥľ
    -0.09
    缺ä¸Ģ
    -0.08
    rieve
    -0.08
     reasonably
    -0.08
    æĤł
    -0.07
    éļ¾æ±Ĥ
    -0.07
    å¯Ľ
    -0.07
    [:,:
    -0.07
    æģ°åĪ°
    -0.07
    éĩij森
    -0.07
    POSITIVE LOGITS
    污
    0.14
    èĦı
    0.14
    æ±ļ
    0.13
    秽
    0.12
     гÑĢÑıз
    0.12
    ä¸įåłª
    0.12
    èĤ®
    0.12
    ç²Ĺ
    0.12
     vulgar
    0.11
    ä¸ijéĻĭ
    0.11
    Activations Density 0.288%

    No Known Activations