© 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. 48114
    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
    æ·±èĵĿ
    -0.07
    å»īä»·
    -0.06
    ç¥ŀä¹ĭ
    -0.06
    为æķ°
    -0.06
    èĮĥçķ´
    -0.06
    ä¹Łæľī
    -0.06
    .har
    -0.06
    çľģéģĵ
    -0.06
    ously
    -0.06
    estroy
    -0.06
    POSITIVE LOGITS
    ALLE
    0.09
    arty
    0.08
    èı
    0.08
    WebRequest
    0.07
    CTYPE
    0.07
    igde
    0.07
    移åĬ¨çīĪ
    0.07
    寵
    0.07
    èīºæľ¯é¦Ĩ
    0.07
     forg
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.