© 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. 47361
    Prev
    Next
    INDEX
    Explanations

    goal, aim, objective

    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
    êng
    -0.07
    à¹īาว
    -0.07
    uto
    -0.07
    Descriptors
    -0.07
    roys
    -0.07
    .define
    -0.06
    uali
    -0.06
    utu
    -0.06
    æľ¬é¢ĺçŃĶæ¡Ī
    -0.06
    ãs
    -0.06
    POSITIVE LOGITS
    klet
    0.07
    åIJİè¿Ľè¡Į
    0.07
    holm
    0.07
    æ¬
    0.07
    atal
    0.07
    -ts
    0.07
    পর
    0.07
    éĿ¡
    0.07
    nock
    0.07
    ä¸ŃåĽ½ç½ij
    0.07
    Activations Density 0.001%

    No Known Activations