© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 17265
    Prev
    Next
    INDEX
    Explanations

    special characters in code/math

    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
    ä¹İ
    -0.06
    :
    -0.06
     Zar
    -0.06
     &
    -0.06
    ;
    -0.06
    ç»§
    -0.06
     n
    -0.06
     fur
    -0.05
     nature
    -0.05
    ä¸Ģè§ī
    -0.05
    POSITIVE LOGITS
    ))/(
    0.10
    ])/
    0.10
    ))/
    0.09
    }while
    0.09
    ]:=
    0.08
    }$/
    0.08
    )$/
    0.08
    ())/
    0.08
    saan
    0.08
    }catch
    0.08
    Activations Density 0.003%

    No Known Activations