© 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. 48686
    Prev
    Next
    INDEX
    Explanations

    alpha, beta-amino acids

    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
    Ùħا
    -0.08
    inha
    -0.08
    inja
    -0.08
    uver
    -0.07
    Ñģки
    -0.07
    |int
    -0.07
    os
    -0.07
    z
    -0.06
    çīį
    -0.06
    gien
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.11
    ï¸İ
    0.10
    ciano
    0.07
    -most
    0.07
     Kud
    0.07
    нкÑĥ
    0.07
    خر
    0.07
    ständ
    0.07
    жай
    0.07
    (?)
    0.07
    Activations Density 0.043%

    No Known Activations