© 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. 8995
    Prev
    Next
    INDEX
    Explanations

    abstract

    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
    /Internal
    -0.07
    交大
    -0.07
     meaningful
    -0.07
    HttpException
    -0.07
    bay
    -0.07
    istö
    -0.07
    æµ·çĽĹ
    -0.07
    ibaldi
    -0.07
    _AL
    -0.07
    etto
    -0.06
    POSITIVE LOGITS
    ãĥIJãĥĬ
    0.07
    صاب
    0.07
    éĥ¨
    0.07
    elui
    0.07
    vari
    0.07
    .function
    0.07
    emann
    0.07
    ause
    0.07
    绪
    0.06
    _FN
    0.06
    Activations Density 0.011%

    No Known Activations