© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23452
    Prev
    Next
    INDEX
    Explanations

    neuronal processes

    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
    ostar
    -0.07
    ino
    -0.07
    aul
    -0.07
    اÙĭ
    -0.07
    æŃ£åıį
    -0.07
    enticate
    -0.06
    ला
    -0.06
    ly
    -0.06
    or
    -0.06
    ¾
    -0.06
    POSITIVE LOGITS
    udin
    0.07
    γÏīν
    0.07
    á»ĭp
    0.07
    à¸ļà¹Ĥà¸ķ
    0.07
    Bindable
    0.07
    Ù°
    0.07
    hma
    0.07
    à¦ļà§įà¦Ľà§ĩ
    0.07
    iht
    0.07
    WidgetItem
    0.07
    Activations Density 0.001%

    No Known Activations