© 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. 9250
    Prev
    Next
    INDEX
    Explanations

    some stuff

    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
    uden
    -0.07
    aliste
    -0.07
    åł
    -0.07
    alus
    -0.07
    roup
    -0.07
    глÑĥ
    -0.07
    _RAD
    -0.07
    herr
    -0.06
     Emm
    -0.06
    ernational
    -0.06
    POSITIVE LOGITS
    èĥ½ä¸į
    0.07
    ÙĬØ·
    0.07
    FRING
    0.07
    MeasureSpec
    0.07
    latlong
    0.06
    触å±ı
    0.06
    δή
    0.06
    天çĽĸ
    0.06
    .jquery
    0.06
    нÑıÑĤ
    0.06
    Activations Density 0.045%

    No Known Activations