© 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. 58204
    Prev
    Next
    INDEX
    Explanations

    translation of language

    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
    PHY
    -0.07
    olino
    -0.06
    <|box_end|>
    -0.06
     disciplined
    -0.06
    çIJĨè®ºåŁºç¡Ģ
    -0.06
    aña
    -0.06
    _algorithm
    -0.06
    WISE
    -0.06
    ä¸ŃåĽ½çĶ»
    -0.06
     photograph
    -0.06
    POSITIVE LOGITS
    ilingual
    0.12
     linguistic
    0.11
     translations
    0.11
    -language
    0.11
     untranslated
    0.10
    æ¯įè¯Ń
    0.10
     lingu
    0.10
     language
    0.10
     Lingu
    0.10
    à¸łà¸²à¸©à¸²
    0.10
    Activations Density 0.251%

    No Known Activations