© 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. 23078
    Prev
    Next
    INDEX
    Explanations

    hexadecimal-like identifiers

    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
    rike
    -0.07
    ÑĢиз
    -0.07
    wij
    -0.06
    æıIJé«ĺå·¥ä½ľæķĪçİĩ
    -0.06
    eza
    -0.06
    quette
    -0.06
    å¨Ĩ
    -0.06
     shovel
    -0.06
    æĬĵ好
    -0.06
    稻èįī
    -0.06
    POSITIVE LOGITS
    rates
    0.08
    oscope
    0.08
    classes
    0.07
    osan
    0.07
    okok
    0.07
    enciales
    0.07
    ndata
    0.07
    oners
    0.07
    ä¸įåĢ¦
    0.07
    kki
    0.07
    Activations Density 0.018%

    No Known Activations