© 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. 14162
    Prev
    Next
    INDEX
    Explanations

    programming code structures

    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
    atik
    -0.07
    agni
    -0.07
    engk
    -0.07
    è´¨éĩıçĽijçĿ£
    -0.07
    ffel
    -0.07
    为ä¸Ģä½ĵçļĦ
    -0.07
    iT
    -0.07
    off
    -0.07
    ç¡
    -0.07
    æ¾İ
    -0.07
    POSITIVE LOGITS
    <|im_end|>
    0.07
    пÑĢе
    0.07
    ↵    ↵↵
    0.07
    ↵      ↵
    0.06
    fum
    0.06
     ?.
    0.06
    _EXCEPTION
    0.06
    ãĢĤï¼Ī
    0.06
    anha
    0.06
    ↵   ↵
    0.06
    Activations Density 0.015%

    No Known Activations