© 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. 56680
    Prev
    Next
    INDEX
    Explanations

    numbers and specific entities

    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
    {@
    -0.07
    stag
    -0.07
    iach
    -0.07
    åĭĭ
    -0.06
    è¿ľè¿ij
    -0.06
    اء
    -0.06
    移åĪ°
    -0.06
    sph
    -0.06
    zyw
    -0.06
    uye
    -0.06
    POSITIVE LOGITS
    anska
    0.07
    adeiras
    0.07
    аÑĤелÑı
    0.07
    icano
    0.07
    èIJ¥ä¸ļé¢Ŀ
    0.07
    anner
    0.07
    emit
    0.07
    alista
    0.07
    akes
    0.07
    èijĨ
    0.07
    Activations Density 0.050%

    No Known Activations