© 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. 42391
    Prev
    Next
    INDEX
    Explanations

    dots followed by punctuation

    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
    ities
    -0.10
    ize
    -0.10
    ings
    -0.09
    psilon
    -0.08
    eral
    -0.08
    ered
    -0.08
    лиз
    -0.08
    lement
    -0.08
    ffect
    -0.08
    istically
    -0.08
    POSITIVE LOGITS
     οÏĢοί
    0.08
    i
    0.08
    en
    0.08
    ellem
    0.08
    à¸ģวà¹Īา
    0.08
    iennes
    0.08
    sem
    0.08
    缸è¾ħ缸æĪIJ
    0.07
     dõi
    0.07
    iou
    0.07
    Activations Density 0.002%

    No Known Activations