© 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. 24524
    Prev
    Next
    INDEX
    Explanations

    Nature and Science journals

    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
    ewa
    -0.07
    ever
    -0.07
    noch
    -0.07
    åŃ£åIJİ
    -0.07
    ewed
    -0.07
    Fore
    -0.06
    å±ij
    -0.06
     Javas
    -0.06
    _ARGUMENT
    -0.06
    足
    -0.06
    POSITIVE LOGITS
    lese
    0.07
    elan
    0.07
    ÃŃst
    0.07
    htë
    0.07
    volver
    0.07
    人åķĬ
    0.06
    æĪijåIJĹ
    0.06
     Obser
    0.06
    fuse
    0.06
    &M
    0.06
    Activations Density 0.010%

    No Known Activations