© 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. 33249
    Prev
    Next
    INDEX
    Explanations

    imaginary

    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
    ÙĨاÙħ
    -0.09
    ijker
    -0.08
    ائÙħ
    -0.08
    tridge
    -0.08
    gether
    -0.08
    ilha
    -0.08
    chter
    -0.08
    å¾·éŁ³
    -0.08
    igung
    -0.08
    æĻ©
    -0.08
    POSITIVE LOGITS
    osaic
    0.07
    åĴĮ
    0.07
    éĥ¨
    0.06
    éĥ¨å°±
    0.06
    éĢļè¿ĩå¼Ģå±ķ
    0.06
    ов
    0.06
    erras
    0.06
    omentum
    0.06
    inary
    0.06
    KeyPressed
    0.06
    Activations Density 0.001%

    No Known Activations