© 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. 38107
    Prev
    Next
    INDEX
    Explanations

    [Fe/H] metallicity

    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
     <<-
    -0.08
    lipp
    -0.08
    ÐŁÐµÑĤеÑĢбÑĥÑĢ
    -0.08
    á»Ĺ
    -0.08
    obr
    -0.08
    ropp
    -0.08
     trÃł
    -0.08
    edImage
    -0.08
    odox
    -0.08
    kol
    -0.08
    POSITIVE LOGITS
    ↵
    0.07
    ↵↵
    0.06
    ä¸ĭåIJĮ
    0.06
    ·
    0.06
     (
    0.06
     e
    0.05
    ®
    0.05
    ——
    0.05
    arat
    0.05
    ducible
    0.05
    Activations Density 0.126%

    No Known Activations