© 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. 7605
    Prev
    Next
    INDEX
    Explanations

    the following

    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
    Ø©
    -0.10
    <|box_end|>
    -0.08
    ETERS
    -0.07
    ation
    -0.07
    estina
    -0.07
    tee
    -0.07
    룬ìĬ¤
    -0.06
    esta
    -0.06
    iers
    -0.06
     nol
    -0.06
    POSITIVE LOGITS
    oret
    0.08
    anged
    0.07
    ×ķ×ĵ
    0.07
    iany
    0.07
    oring
    0.07
    iring
    0.07
     usual
    0.07
    常说çļĦ
    0.07
    è´¨çļĦ
    0.06
     compi
    0.06
    Activations Density 0.002%

    No Known Activations