© 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. 63977
    Prev
    Next
    INDEX
    Explanations

    matrix and quaternion operations

    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
    _TUN
    -0.09
    lage
    -0.08
    arella
    -0.08
    jte
    -0.07
    çĤķ
    -0.07
    交åĩº
    -0.07
    Utc
    -0.07
    ibs
    -0.07
    åįģäºĮçĶŁèĤĸ
    -0.07
    ulta
    -0.07
    POSITIVE LOGITS
     represented
    0.11
    represented
    0.09
     representing
    0.09
     repres
    0.08
     Representation
    0.08
     composed
    0.08
     Represent
    0.08
     reprezent
    0.08
    repr
    0.08
    Representation
    0.08
    Activations Density 0.151%

    No Known Activations