© 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. 27971
    Prev
    Next
    INDEX
    Explanations

    foreign language 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
    æĹ¢åı¯
    -0.07
     legitimately
    -0.07
    æĩ¦
    -0.07
    tection
    -0.07
    CEPT
    -0.07
    èݱçī¹
    -0.07
     ÑģÑĤоÑĢон
    -0.07
     sis
    -0.06
    .pk
    -0.06
    sted
    -0.06
    POSITIVE LOGITS
    rypt
    0.07
    tw
    0.07
    ym
    0.07
    tl
    0.07
     Hack
    0.07
    föl
    0.07
    YM
    0.06
     ìĺģ
    0.06
    cot
    0.06
    tene
    0.06
    Activations Density 0.001%

    No Known Activations