© 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. 8901
    Prev
    Next
    INDEX
    Explanations

    code delimiters and numbers

    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
    ä½ķãģ§ãĤĤ
    -0.07
    uum
    -0.07
    iram
    -0.07
    éĽªå³°
    -0.07
    PJ
    -0.06
    ä¸ĢæĿ¡è¡Ĺ
    -0.06
    uver
    -0.06
    orgia
    -0.06
    olucion
    -0.06
    åĮĹ京çļĦ
    -0.06
    POSITIVE LOGITS
    chts
    0.07
    åij¨èº«
    0.07
    鬣
    0.07
    ä¸ĥ大
    0.07
     rót
    0.07
     Cours
    0.07
    klen
    0.07
    èĤĩ
    0.07
    ugins
    0.07
    coli
    0.06
    Activations Density 0.036%

    No Known Activations