© 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. 57912
    Prev
    Next
    INDEX
    Explanations

    directory paths or environment variables

    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
    /ay
    -0.07
    /flutter
    -0.07
    åį«ä¸ľ
    -0.07
    κε
    -0.07
    اÙĨÙĩ
    -0.07
    éĩįè¦ģçļĦæĺ¯
    -0.07
    _stdio
    -0.07
    estan
    -0.07
    plor
    -0.07
     Teixe
    -0.07
    POSITIVE LOGITS
    agrant
    0.08
    ãģ«ãģĤãĤĭ
    0.07
    -mounted
    0.07
    é¦ĸéĥ¨
    0.07
    PATH
    0.07
    :/
    0.06
    thinkable
    0.06
    éļĨ
    0.06
     newPath
    0.06
    icine
    0.06
    Activations Density 0.100%

    No Known Activations