© 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. 18413
    Prev
    Next
    INDEX
    Explanations

    about an axis

    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
    Ñģен
    -0.08
    idar
    -0.08
    weise
    -0.08
    wiat
    -0.08
    cito
    -0.07
    åĿıäºĭ
    -0.07
    å¼Ģæĭĵè¿Ľåıĸ
    -0.07
    æĬĬåħ³
    -0.07
    ups
    -0.07
    hoe
    -0.07
    POSITIVE LOGITS
    /about
    0.08
    ä¸Ģ个
    0.08
     axes
    0.07
     centre
    0.07
    /on
    0.07
    /off
    0.06
     axis
    0.06
    andon
    0.06
    /from
    0.06
    roker
    0.06
    Activations Density 0.006%

    No Known Activations