© 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. 4301
    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
    STRUCTOR
    -0.09
    iliun
    -0.09
    οÏħÏģγ
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    为å¸Ī
    -0.08
    ä¸ĭåIJĮ
    -0.08
    èĢĮéĻį
    -0.08
    иÑģÑĤÑĢа
    -0.08
    éĺħè¯»æľ¬æĸĩåīį
    -0.08
    ileo
    -0.08
    POSITIVE LOGITS
    ebel
    0.06
     re
    0.06
    解
    0.06
     outright
    0.06
    ä¸Ģä¸ĭåIJ§
    0.06
     Futures
    0.06
    axed
    0.06
     v
    0.06
    åģĩ
    0.06
    irements
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.