© 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. 61992
    Prev
    Next
    INDEX
    Explanations

    works, films, games, or albums

    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
     factors
    -0.06
    ä½İä¸ĭ
    -0.06
     who
    -0.06
    adden
    -0.06
    æĿ
    -0.06
     Spo
    -0.06
    ampen
    -0.06
    al
    -0.05
    åĽłç´łçļĦ
    -0.05
    etz
    -0.05
    POSITIVE LOGITS
     flagship
    0.13
     portfolio
    0.11
    ä»£è¡¨ä½ľ
    0.11
    portfolio
    0.10
    /portfolio
    0.10
     portf
    0.09
    ç³»åĪĹçļĦ
    0.09
    Portfolio
    0.09
    å¾ĹæĦı
    0.09
    éĶIJæĦı
    0.09
    Activations Density 0.770%

    No Known Activations