© 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. 13591
    Prev
    Next
    INDEX
    Explanations

    butterflyfish, rabbitfish, asparagus fern

    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
    zerw
    -0.08
    erber
    -0.07
    ERTO
    -0.07
    roda
    -0.07
    aum
    -0.07
    å¿įçĿĢ
    -0.07
    å¿į
    -0.07
    à¹Ĥà¸Ľà¸£à¸Ķ
    -0.07
    istem
    -0.06
    _APPRO
    -0.06
    POSITIVE LOGITS
    ĥ
    0.08
    ÑĢалÑĮ
    0.07
    丹
    0.06
    Òĵ
    0.06
    ATE
    0.06
    à¸ľ
    0.06
     Extended
    0.06
    å¤ļå°ij个
    0.06
    éĤ£æĺ¯æĪij
    0.06
    جب
    0.06
    Activations Density 1.540%

    No Known Activations