© 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. 17479
    Prev
    Next
    INDEX
    Explanations

    "as well as" phrases

    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
    ppy
    -0.08
    igia
    -0.08
    _mut
    -0.07
    xed
    -0.07
    stras
    -0.07
    ersen
    -0.07
    igd
    -0.07
    Ø®ÙĬ
    -0.07
    éĻIJãĤĬ
    -0.07
    mut
    -0.07
    POSITIVE LOGITS
    ãģ¨ãĤĤãģ«
    0.08
    obel
    0.06
     respectively
    0.06
    aut
    0.06
    -addon
    0.06
    -toolbar
    0.06
    ä½łè¯´çļĦ
    0.06
    ucci
    0.06
    -season
    0.06
    丽èİİ
    0.06
    Activations Density 0.422%

    No Known Activations