© 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. 56448
    Prev
    Next
    INDEX
    Explanations

    programming code loops

    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
    -
    -0.08
    "
    -0.07
     -
    -0.07
     /
    -0.06
     Klar
    -0.06
    ied
    -0.06
    /
    -0.06
    K
    -0.06
     mand
    -0.06
     defeats
    -0.06
    POSITIVE LOGITS
    úd
    0.10
    zion
    0.09
    еÑĩаÑĤ
    0.08
    éĩľ
    0.08
    battle
    0.08
    uves
    0.08
    åķĨæĬ¥
    0.08
    teve
    0.08
    Ø·ÙĨ
    0.08
     hava
    0.08
    Activations Density 0.123%

    No Known Activations