© 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. 50644
    Prev
    Next
    INDEX
    Explanations

    G, rad, cent, cGy, G

    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
    ianto
    -0.07
    ero
    -0.07
    alborg
    -0.07
    tpl
    -0.07
    erver
    -0.07
    ç¾Ķ
    -0.07
     Auc
    -0.07
     Grie
    -0.07
    igt
    -0.06
    亿欧åħĥ
    -0.06
    POSITIVE LOGITS
    olumbia
    0.09
    hos
    0.08
     UCLA
    0.07
    CTR
    0.07
    icago
    0.07
    CIO
    0.07
     Calif
    0.07
     Pasadena
    0.07
    çħ§çĽ¸
    0.07
    á»Ļn
    0.07
    Activations Density 0.006%

    No Known Activations