© 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. 7617
    Prev
    Next
    INDEX
    Explanations

    Christmas Krampus sweater, neural network models, fluorescent beads, Scriptable Object Instance, text files, triangular shape, string snare, cyborg dragonflies

    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
    ä¸įæ¸Ŀ
    -0.09
    ymar
    -0.09
    धà¥Ģ
    -0.09
    olian
    -0.08
    åĢ¼æѤ
    -0.08
    æĭĭ
    -0.08
    emean
    -0.08
    PELL
    -0.08
    etur
    -0.08
    olÃŃ
    -0.08
    POSITIVE LOGITS
    immel
    0.08
    çĶ¨ä½ľ
    0.07
    -
    0.06
     instead
    0.06
     whose
    0.06
    å¹¿æ³Ľ
    0.06
    æľīåĬ©
    0.06
    +
    0.06
     widely
    0.06
     inspired
    0.06
    Activations Density 0.309%

    No Known Activations