© 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. 18086
    Prev
    Next
    INDEX
    Explanations

    exponents

    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
    ترا
    -0.07
    fi
    -0.07
     lur
    -0.07
    éĿ¢æĹł
    -0.07
    çIJīçĴĥ
    -0.07
    Ñħодил
    -0.06
     éch
    -0.06
     teb
    -0.06
    ä»ķ
    -0.06
    éĻ¸
    -0.06
    POSITIVE LOGITS
    å·´æĭī
    0.08
     Obser
    0.07
    insky
    0.07
    MBER
    0.07
     ÙĪØ¥ÙĦÙī
    0.07
    BaseContext
    0.07
    ãĥ©ãĥľ
    0.07
     #__
    0.07
    Invoker
    0.07
    issy
    0.07
    Activations Density 0.001%

    No Known Activations