© 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. 13516
    Prev
    Next
    INDEX
    Explanations

    scientific citations

    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
    нÑĮ
    -0.08
    oot
    -0.08
    Å¡t
    -0.08
    orest
    -0.07
    éĵĽ
    -0.07
    bem
    -0.07
    arang
    -0.07
    aku
    -0.07
    ETO
    -0.07
    è¡Ĩ
    -0.07
    POSITIVE LOGITS
    oces
    0.07
    _NB
    0.07
    unos
    0.07
    ionale
    0.06
    ités
    0.06
    è¾Ľäº¥
    0.06
    logs
    0.06
    yer
    0.06
    ecke
    0.06
    ugier
    0.06
    Activations Density 0.031%

    No Known Activations