© 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. 9645
    Prev
    Next
    INDEX
    Explanations

    tricarboxylic acid cycle intermediates and enzymes

    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
    å¾·åįİ
    -0.08
    ï¼Ŀï¼Ŀï¼Ŀï¼Ŀ
    -0.08
     Ballard
    -0.08
    zeni
    -0.08
    ither
    -0.08
    izoph
    -0.08
    åįĹçľģ
    -0.08
    /null
    -0.08
    iles
    -0.07
    ritz
    -0.07
    POSITIVE LOGITS
    éĨĭ
    0.07
    ograd
    0.07
    Õ¡
    0.07
    crypt
    0.07
    ắng
    0.06
    £
    0.06
    acus
    0.06
    å°±è§ģ
    0.06
     diety
    0.06
    ÑĩеÑĤ
    0.06
    Activations Density 0.029%

    No Known Activations