© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13615
    Prev
    Next
    INDEX
    Explanations

    code structure markers

    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
    izia
    -0.07
    æķ¬ç¤¼
    -0.07
    ober
    -0.07
    hton
    -0.07
    VD
    -0.07
    дноÑģÑĤи
    -0.06
    нан
    -0.06
    _APPS
    -0.06
    è¤
    -0.06
    dul
    -0.06
    POSITIVE LOGITS
    ":{"
    0.08
    çĻ¾å®¶
    0.07
    ondo
    0.07
    OMIC
    0.07
    ':{'
    0.07
    âĨĵâĨĵ
    0.07
    settings
    0.07
    ÏĥÏĦι
    0.07
    enix
    0.07
    parameters
    0.06
    Activations Density 0.277%

    No Known Activations