© 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. 40902
    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
    å·¥ä½ľé¡ºåĪ©
    -0.07
     influence
    -0.07
    庸
    -0.06
     clos
    -0.06
    rhs
    -0.06
    NDER
    -0.06
     Influence
    -0.06
    èľľ
    -0.06
    å®ł
    -0.06
    èIJ½å¹ķ
    -0.06
    POSITIVE LOGITS
    åįķéĹ´
    0.08
    entak
    0.08
     |+
    0.08
     maximize
    0.07
    ighton
    0.07
    ATUR
    0.07
     parallel
    0.07
    æľĢ大éĻIJåº¦åľ°
    0.07
    åı¶éħ¸
    0.07
    vide
    0.07
    Activations Density 0.000%

    No Known Activations