© 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. 56024
    Prev
    Next
    INDEX
    Explanations

    punctuation and then

    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
    ÏĥÏĦε
    -0.08
    éħ¸çĶľèĭ¦è¾£
    -0.08
    Yii
    -0.08
    ahari
    -0.08
    éħ¸è¾£
    -0.08
    _RCC
    -0.07
    ÙıÙĪ
    -0.07
    áŁĤ
    -0.07
    eppe
    -0.07
    idebar
    -0.07
    POSITIVE LOGITS
    (
    0.07
    cott
    0.06
     Perd
    0.06
    çĻ¾äºĭ
    0.06
    [
    0.06
     McGr
    0.06
    wijk
    0.06
    ë©´
    0.05
     (
    0.05
     nearly
    0.05
    Activations Density 0.076%

    No Known Activations