© 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. 48375
    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
    łĢ
    -0.07
    为è¾ħ
    -0.07
     Tiong
    -0.07
    stek
    -0.07
     jung
    -0.07
    oldem
    -0.07
    .gs
    -0.06
     gründ
    -0.06
    ndo
    -0.06
     Fixes
    -0.06
    POSITIVE LOGITS
    ostro
    0.07
    aji
    0.07
     distinguishing
    0.07
    idente
    0.07
    иÑĩ
    0.06
    çī¹æĢ§çļĦ
    0.06
    iku
    0.06
    itest
    0.06
     machine
    0.06
     MACHINE
    0.06
    Activations Density 0.000%

    No Known Activations