© 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. 29674
    Prev
    Next
    INDEX
    Explanations

    triple letter aba

    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
    ings
    -0.09
    empf
    -0.08
    hir
    -0.08
    ãĢħ
    -0.08
    ä¸īå°º
    -0.08
    enges
    -0.08
    ottie
    -0.08
    ary
    -0.08
    ordi
    -0.07
    orest
    -0.07
    POSITIVE LOGITS
    añ
    0.08
    esus
    0.07
    æµ·å½Ĵ
    0.07
    espo
    0.06
    rypto
    0.06
    esión
    0.06
    oire
    0.06
    bing
    0.06
    ¼
    0.06
    SourceType
    0.06
    Activations Density 0.007%

    No Known Activations