© 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. 4000
    Prev
    Next
    INDEX
    Explanations

    location name

    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
    anka
    -0.07
    Truthy
    -0.06
    ä¸Ģ空
    -0.06
    wai
    -0.06
    ×IJת
    -0.06
    lu
    -0.06
    æĪ·
    -0.06
    寸
    -0.06
     Mol
    -0.06
     setattr
    -0.06
    POSITIVE LOGITS
    ieber
    0.08
    ä¸įå¾Ĺ以任ä½ķ
    0.07
    uchos
    0.07
    represented
    0.07
    ymes
    0.07
    stin
    0.07
    åĪĨ享èĩ³
    0.07
    è´µåľ¨
    0.07
     Apresentação
    0.07
    rch
    0.07
    Activations Density 0.288%

    No Known Activations