© 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. 30899
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    //"
    -0.09
    //(
    -0.08
    Continua
    -0.08
    _arrays
    -0.08
    //[
    -0.08
     Détails
    -0.08
    texte
    -0.08
    δια
    -0.08
    cers
    -0.07
    arded
    -0.07
    POSITIVE LOGITS
    azos
    0.08
    aging
    0.08
     dev
    0.06
    å¶
    0.06
    ufs
    0.06
     dt
    0.06
     dator
    0.06
    æĭĵ
    0.05
    uiten
    0.05
    asing
    0.05
    Activations Density 0.000%

    No Known Activations