© 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. 29527
    Prev
    Next
    INDEX
    Explanations

    function and def definitions

    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
    袴
    -0.08
     Synthetic
    -0.07
     Alco
    -0.07
    ställ
    -0.07
     Acr
    -0.07
     synthetic
    -0.07
    ibaldi
    -0.07
    zett
    -0.07
    .Fields
    -0.07
    ield
    -0.06
    POSITIVE LOGITS
    æķıæĦŁ
    0.09
    ReLU
    0.08
    åĩ½æķ°çļĦ
    0.08
    åĩ½æķ°
    0.08
    creasing
    0.07
    æĺłå°Ħ
    0.07
     sensitive
    0.07
    arit
    0.07
    afen
    0.07
    éĸ¢
    0.07
    Activations Density 0.013%

    No Known Activations