© 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. 63393
    Prev
    Next
    INDEX
    Explanations

    abstract methods

    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
    çİĭ大
    -0.08
     Bima
    -0.08
    ERM
    -0.07
    PWD
    -0.07
    æĺĶ
    -0.07
    umine
    -0.07
    iane
    -0.07
    pez
    -0.07
    erb
    -0.07
     пÑĢиÑĪ
    -0.07
    POSITIVE LOGITS
    by
    0.08
     by
    0.07
     abstract
    0.07
    elaar
    0.06
    roe
    0.06
    abstract
    0.06
    [J
    0.06
    avour
    0.06
    款
    0.06
    æĪIJ家
    0.06
    Activations Density 1.151%

    No Known Activations