© 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. 27414
    Prev
    Next
    INDEX
    Explanations

    legal jargon or suffixes

    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
    es
    -0.12
    寺
    -0.12
    ¿
    -0.11
    ers
    -0.11
    ersh
    -0.10
    esm
    -0.10
    áĢ¸
    -0.10
    erse
    -0.10
    ism
    -0.10
    еÑģ
    -0.10
    POSITIVE LOGITS
    åijĺ
    0.13
    ı
    0.12
    åĵ¡
    0.11
    åijĺçļĦ
    0.10
    ao
    0.10
    اء
    0.10
    um
    0.10
    °
    0.09
    ованиÑı
    0.09
    éĩı
    0.09
    Activations Density 1.479%

    No Known Activations