© 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. 63530
    Prev
    Next
    INDEX
    Explanations

    DISPLAY TITLE or limits

    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
    ãĤ£
    -0.08
    ibernate
    -0.08
    ONUS
    -0.07
    lander
    -0.07
    urally
    -0.07
    ждÑĭ
    -0.07
    icap
    -0.07
    esito
    -0.07
    ê¹IJ
    -0.07
    ility
    -0.07
    POSITIVE LOGITS
    åįģæĹ¥
    0.07
    éĢį
    0.07
    udent
    0.07
    quad
    0.06
    Ø®ÙĨ
    0.06
    itto
    0.06
    rej
    0.06
    bord
    0.06
    ł
    0.06
    engin
    0.06
    Activations Density 0.001%

    No Known Activations