© 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. 56189
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by code-like strings

    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
    berry
    -0.07
    aldas
    -0.07
    "https
    -0.06
    resse
    -0.06
    born
    -0.06
    ä¸įåıij
    -0.06
    berries
    -0.06
    ian
    -0.06
    IAN
    -0.06
    burger
    -0.06
    POSITIVE LOGITS
    说æĸĩ
    0.07
    enton
    0.07
     formatos
    0.07
    ¿
    0.07
    দà§įধ
    0.06
    åıĺæķħ
    0.06
     Conn
    0.06
    ित
    0.06
     Wilkinson
    0.06
    åĮħåIJ«çĿĢ
    0.06
    Activations Density 0.076%

    No Known Activations