© 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. 1552
    Prev
    Next
    INDEX
    Explanations

    articles before descriptive words

    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
    ÙĨÙĬÙĨ
    -0.10
    äºijæ·¡
    -0.09
    Ãło
    -0.07
    raphe
    -0.07
    ä¸ĩä¼Ĺ
    -0.07
    彬彬
    -0.07
    bsp
    -0.07
    orro
    -0.07
    _normalized
    -0.07
    ppard
    -0.07
    POSITIVE LOGITS
    estruct
    0.07
    plied
    0.07
     part
    0.07
    ãģĤãģı
    0.06
    verse
    0.06
     "
    0.06
     primarily
    0.06
     Ñģвоего
    0.06
    åĶ¯
    0.06
     Ergän
    0.06
    Activations Density 0.175%

    No Known Activations