© 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. 12390
    Prev
    Next
    INDEX
    Explanations

    , [ , foo

    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¸įè¾ŀ
    -0.07
    åĿIJä¸Ĭ
    -0.07
    ayo
    -0.07
    alik
    -0.06
    à®°
    -0.06
    aglio
    -0.06
    éħĮ
    -0.06
     currently
    -0.06
    dere
    -0.06
    tox
    -0.06
    POSITIVE LOGITS
    urgia
    0.08
    çĮĽ
    0.07
    erialized
    0.07
    足
    0.07
    odia
    0.07
    è¿Ľåıĸ
    0.07
    kia
    0.07
    åį´ä¾ĿçĦ¶
    0.07
    etus
    0.07
     menda
    0.07
    Activations Density 0.046%

    No Known Activations