© 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. 20413
    Prev
    Next
    INDEX
    Explanations

    "{", "{" 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
    imenta
    -0.08
    ities
    -0.08
    owell
    -0.08
    ÑĢке
    -0.08
    idades
    -0.08
    ernet
    -0.07
    oftware
    -0.07
    edio
    -0.07
    iace
    -0.07
    irected
    -0.07
    POSITIVE LOGITS
    nowled
    0.09
    йÑĤ
    0.08
    umuman
    0.08
    rial
    0.08
    stein
    0.08
    nowledge
    0.08
    let
    0.07
    lesia
    0.07
    Ķ
    0.07
    tober
    0.07
    Activations Density 0.004%

    No Known Activations