© 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. 42127
    Prev
    Next
    INDEX
    Explanations

    digit, clerk, analyst, policy, system

    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
    sWith
    -0.17
    swith
    -0.12
    sson
    -0.11
    ther
    -0.10
    to
    -0.10
    the
    -0.10
    ships
    -0.09
    ãģ¦ãĤĤ
    -0.09
    th
    -0.09
    ss
    -0.09
    POSITIVE LOGITS
    cape
    0.13
    heets
    0.13
    ysteem
    0.12
    pring
    0.12
    peed
    0.11
    weeney
    0.11
    cales
    0.11
    ourced
    0.11
    cribe
    0.10
    nya
    0.10
    Activations Density 1.424%

    No Known Activations