© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20561
    Prev
    Next
    INDEX
    Explanations

    Grand Prix

    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
    MT
    -0.06
    enne
    -0.06
     Eg
    -0.06
    usz
    -0.06
    åĩīæ°´
    -0.06
     Barnett
    -0.06
    _fd
    -0.06
     Vigil
    -0.05
    OV
    -0.05
    Mat
    -0.05
    POSITIVE LOGITS
    [array
    0.08
    argon
    0.08
    onsin
    0.08
    onton
    0.08
    rary
    0.08
    alde
    0.07
     Diá»ĩu
    0.07
    <<<<<<<
    0.07
    eley
    0.07
    ebol
    0.07
    Activations Density 0.262%

    No Known Activations