© 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. 43861
    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
    å¾ħ
    -0.07
    ourage
    -0.07
     végét
    -0.06
    fuse
    -0.06
    å¾ħéģĩ
    -0.06
    fuÃŁ
    -0.06
    оÑĢг
    -0.06
     vare
    -0.06
    óf
    -0.06
    ress
    -0.06
    POSITIVE LOGITS
    иÑģпÑĥÑģка
    0.07
    é£ŀ天
    0.07
    ceased
    0.07
    림
    0.07
    ä¸įåŃĺåľ¨
    0.07
    WN
    0.07
    ceg
    0.07
    ernel
    0.07
    zil
    0.07
    Ñģпали
    0.07
    Activations Density 0.000%

    No Known Activations