© 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. 9295
    Prev
    Next
    INDEX
    Explanations

    threshold, binding, constraint

    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
    OND
    -0.08
    ondi
    -0.08
     mum
    -0.07
    elij
    -0.07
    ä¸Ģæ¦Ĥ
    -0.07
     cul
    -0.07
    ον
    -0.07
    throw
    -0.07
    _enter
    -0.07
     mute
    -0.07
    POSITIVE LOGITS
     sfr
    0.09
     Constraint
    0.08
    éºŁ
    0.08
    ãĤ®ãĥª
    0.08
    /max
    0.07
    à¸ŀà¸Ńà¸Ķี
    0.07
     brink
    0.07
    æľĢ大åĮĸ
    0.07
    æĿŀ
    0.07
     maxim
    0.07
    Activations Density 0.004%

    No Known Activations