© 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. 62547
    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
    ople
    -0.08
    вÑĸÑĢ
    -0.07
    elper
    -0.07
    itse
    -0.07
    uban
    -0.07
    ilu
    -0.07
    ile
    -0.07
    å°½
    -0.07
    åIJİè¿Ľ
    -0.06
    乡åİ¿
    -0.06
    POSITIVE LOGITS
    马åħĭæĢĿ主ä¹ī
    0.08
    astas
    0.08
    haj
    0.07
    à¸įา
    0.07
     undermin
    0.07
    èĥ½å¤Łä»İ
    0.07
     поднима
    0.07
    stens
    0.07
    æĨ¬
    0.07
    没æŶéĹ´
    0.07
    Activations Density 0.000%

    No Known Activations