© 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. 47995
    Prev
    Next
    INDEX
    Explanations

    male and female characters

    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
    è¿Ļ两ç§į
    -0.08
    æĹ¢åı¯
    -0.07
    åħ¼
    -0.07
    è¿Ļé¡¹å·¥ä½ľ
    -0.07
    两ç§įæĸ¹å¼ı
    -0.07
    çĽĪçĽĪ
    -0.07
    ellent
    -0.07
    quam
    -0.06
    éĤ£çĤ¹
    -0.06
    .models
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.18
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.17
    çļĦåIJĦ项
    0.13
    åĮħæĭ¬
    0.13
    主è¦ģåĮħæĭ¬
    0.12
    —including
    0.12
    åIJĦ项
    0.12
    諸
    0.12
    çļĦä¸Ģç³»åĪĹ
    0.12
     including
    0.12
    Activations Density 1.418%

    No Known Activations