© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 50678
    Prev
    Next
    INDEX
    Explanations

    code comment delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     whatever
    -0.08
    whatever
    -0.08
    Âł
    -0.06
    è¿Ļä¸ľè¥¿
    -0.06
    éļıçĿĢæĹ¶éĹ´çļĦ
    -0.06
    ä»ĸ们çļĦ
    -0.06
     indeed
    -0.06
    åĩºäºº
    -0.06
     Through
    -0.06
    ä¸ĩä¸Ī
    -0.06
    POSITIVE LOGITS
     }):
    0.10
    )):
    0.10
    }):
    0.10
    >):
    0.10
    )':
    0.09
    "):
    0.09
    ]):
    0.09
     ):
    0.09
     {}:
    0.09
    '):
    0.08
    Activations Density 0.054%

    No Known Activations