© 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. 56832
    Prev
    Next
    INDEX
    Explanations

    versions or variants

    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
    olec
    -0.09
    adini
    -0.08
    çªŁ
    -0.08
    RootElement
    -0.08
    affen
    -0.08
    ffy
    -0.08
    zec
    -0.08
    /favicon
    -0.08
    aliz
    -0.07
    éĩijèĬ±
    -0.07
    POSITIVE LOGITS
    versions
    0.12
     versions
    0.11
     portion
    0.11
     portions
    0.10
     Variant
    0.10
     variants
    0.10
     variant
    0.10
     version
    0.10
    çīĪæľ¬çļĦ
    0.10
    version
    0.10
    Activations Density 1.272%

    No Known Activations