© 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. 4315
    Prev
    Next
    INDEX
    Explanations

    romance and love stories

    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
    é«
    -0.08
    éĿĴæĿ¾
    -0.07
    å¨ĺ家
    -0.07
    æĶ¹è¿Ľ
    -0.07
    为èį£
    -0.07
    端
    -0.07
    æłĭæ¢ģ
    -0.07
    åĨ·æ±Ĺ
    -0.07
    èĦĬæ¢ģ
    -0.07
    uden
    -0.07
    POSITIVE LOGITS
     romant
    0.12
     romantic
    0.11
     romance
    0.11
    çĶľèľľ
    0.10
    æĦŁæĥħ
    0.10
    ç¼łç»µ
    0.10
    çĪ±æĥħ
    0.10
     Romantic
    0.09
    çĪ±æĥħæķħäºĭ
    0.09
    çĪ±æĥħçļĦ
    0.09
    Activations Density 0.138%

    No Known Activations