© 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. 55797
    Prev
    Next
    INDEX
    Explanations

    Project-Id-Version or expected output

    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
    åįķæīĭ
    -0.07
    colas
    -0.07
    ingos
    -0.07
    lieb
    -0.07
    éĿĴåħī
    -0.06
    mej
    -0.06
    zim
    -0.06
    arty
    -0.06
     Negeri
    -0.06
    åĪĨãģij
    -0.06
    POSITIVE LOGITS
    æĺŃ
    0.08
    èĮī
    0.08
    æk
    0.08
    éķĩä¸Ńå¿ĥ
    0.07
    æģª
    0.07
    å³¥åµĺ
    0.07
    raž
    0.07
    å°ģè£ħ
    0.07
    ÏĨη
    0.07
    _expect
    0.06
    Activations Density 0.001%

    No Known Activations