© 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. 11483
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    K
    -0.06
    as
    -0.06
    L
    -0.06
    orst
    -0.06
    orie
    -0.06
    at
    -0.06
    好äºĭ
    -0.06
    en
    -0.06
    ie
    -0.06
    aze
    -0.06
    POSITIVE LOGITS
    literal
    0.09
    egov
    0.09
    maq
    0.08
    caret
    0.08
    .Gray
    0.08
    manos
    0.08
    ownik
    0.08
    postal
    0.08
    .AI
    0.08
    åį³éĢĿ
    0.08
    Activations Density 0.017%

    No Known Activations