© 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. 31705
    Prev
    Next
    INDEX
    Explanations

    coordinates / position

    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
    æµģ
    -0.07
    bert
    -0.07
    uding
    -0.07
    ä¸įåħį
    -0.06
    unar
    -0.06
    paring
    -0.06
    _der
    -0.06
    ãģ©
    -0.06
    <F
    -0.06
    qm
    -0.06
    POSITIVE LOGITS
    áº
    0.10
     coordinates
    0.09
     somewhere
    0.08
    æŃ£å¼ıæĪIJç«ĭ
    0.07
    coordinates
    0.07
    æݨåĭķ
    0.07
     Coordinates
    0.07
    æ¿
    0.07
    hoff
    0.07
    KNOWN
    0.07
    Activations Density 0.004%

    No Known Activations