© 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. 42749
    Prev
    Next
    INDEX
    Explanations

    COURT,DIVISION,APPEAL,DISTRICT

    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
     Carm
    -0.06
    afil
    -0.06
    icas
    -0.06
    itol
    -0.06
    æĸĻ
    -0.06
     certified
    -0.06
    athed
    -0.06
    adow
    -0.06
    /tiny
    -0.06
    æĻĹ
    -0.06
    POSITIVE LOGITS
    tpl
    0.09
    ä¸ĢæĪIJ
    0.08
    reuse
    0.08
    IVES
    0.08
    morgan
    0.08
    INES
    0.08
    alej
    0.08
    ÅĽni
    0.08
    лÑĮ
    0.08
    ãĥ¼ãĥĹ
    0.08
    Activations Density 0.007%

    No Known Activations