© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14028
    Prev
    Next
    INDEX
    Explanations

    common feature or universal trait

    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
    -tool
    -0.07
    _tool
    -0.07
    å¿ĥèĥ¸
    -0.07
    çĺ¾
    -0.07
    toi
    -0.07
    ozo
    -0.07
    tool
    -0.07
    akh
    -0.07
    Tool
    -0.06
     Tool
    -0.06
    POSITIVE LOGITS
    åħ±éĢļ
    0.13
    åħ±æĢ§
    0.13
    åħ±åIJĮçļĦ
    0.12
    çļĦåħ±åIJĮ
    0.12
    åħ±åIJĮ
    0.12
     ê³µíĨµ
    0.11
     shared
    0.11
    éĢļçĶ¨çļĦ
    0.10
     Ùħشتر
    0.10
     universal
    0.10
    Activations Density 0.209%

    No Known Activations