© 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. 51485
    Prev
    Next
    INDEX
    Explanations

    gap and distance or year or between

    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
    ä¸įè¡°
    -0.09
    ering
    -0.09
    erge
    -0.08
     ulang
    -0.08
    ä¸įåĢ¦
    -0.08
    quê
    -0.08
    éĿłè°±çļĦ
    -0.08
    ĥ
    -0.08
    гÑĢад
    -0.08
    ered
    -0.08
    POSITIVE LOGITS
    ness
    0.09
    less
    0.09
    wise
    0.08
    sters
    0.08
    lessly
    0.08
     Between
    0.08
     between
    0.08
    éļĻ
    0.08
    åı£çļĦ
    0.08
    ner
    0.08
    Activations Density 0.010%

    No Known Activations