© 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. 30224
    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
    èĭ¦èĭ¦
    -0.08
    à¤ĸा
    -0.08
    ä¸Ģ个人çļĦ
    -0.07
    âĵĴ
    -0.07
    oop
    -0.07
    ieder
    -0.07
    è¹Ī
    -0.07
     Spare
    -0.07
     Chow
    -0.07
     evacu
    -0.07
    POSITIVE LOGITS
    Ł
    0.08
    çIJ¢
    0.07
    __.__
    0.07
    owski
    0.07
    byn
    0.07
     pele
    0.07
    ighton
    0.06
     pev
    0.06
    以å¾ħ
    0.06
     Statements
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.