© 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. 58022
    Prev
    Next
    INDEX
    Explanations

    this time

    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
    以ä¸ĭåĩł
    -0.09
     λοι
    -0.08
    åĬ¨èĦī硬åĮĸ
    -0.08
    anon
    -0.07
    ãĤĴãĤģ
    -0.07
     abit
    -0.07
    Äĵt
    -0.07
    RunWith
    -0.07
    æľīéĻIJ责任
    -0.07
    anita
    -0.07
    POSITIVE LOGITS
     rd
    0.07
     M
    0.06
    _snapshot
    0.06
    壹
    0.06
    /span
    0.06
    æľīè¿Ļ个
    0.06
    ól
    0.06
     mac
    0.06
    è½
    0.06
    WM
    0.06
    Activations Density 0.806%

    No Known Activations