© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61777
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    çī¹æ®ĬçļĦ
    -0.07
    å°Ķçī¹
    -0.07
    ä½³
    -0.07
    _ORD
    -0.07
    }s
    -0.07
    æīĢ以就
    -0.07
    ç»ĻæĪij们带æĿ¥
    -0.07
    eldes
    -0.07
    微信æī«ä¸Ģæī«
    -0.06
    porto
    -0.06
    POSITIVE LOGITS
    æĽ´ç¬¦åIJĪ
    0.07
    米
    0.07
    ä¸įåħį
    0.07
    è½»åŀĭ
    0.07
    ä¸Ģèĩ´æĢ§
    0.07
    ÙĦاÙģ
    0.07
    离岸
    0.07
    antal
    0.07
    æĺµ
    0.07
    ä¸ĢæĿ¡é¾Ļ
    0.06
    Activations Density 0.015%

    No Known Activations