© 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. 26661
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ingly
    -0.08
    obi
    -0.08
    ogy
    -0.07
    ocracy
    -0.07
    åİ»ä½ķ
    -0.07
    ally
    -0.07
    нок
    -0.07
    ®
    -0.07
    ers
    -0.06
    пеÑĢа
    -0.06
    POSITIVE LOGITS
    'util
    0.07
    _abort
    0.07
    Util
    0.07
    rd
    0.07
    bit
    0.07
    rt
    0.07
    vide
    0.07
    util
    0.07
    _util
    0.07
    _utils
    0.06
    Activations Density 0.000%

    No Known Activations