© 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. 48399
    Prev
    Next
    INDEX
    Explanations

    documentation, projects, version, description

    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
    ...).
    -0.07
    /
    -0.07
    -
    -0.07
    ).\
    -0.06
    associated
    -0.06
    æĥħåĨµçŃī
    -0.06
     associated
    -0.06
    epro
    -0.06
    )."
    -0.06
    öst
    -0.06
    POSITIVE LOGITS
    overe
    0.08
    schlieÃŁlich
    0.08
    _:
    0.08
     maje
    0.08
    aille
    0.07
    enties
    0.07
     **:
    0.07
    @c
    0.07
     REGARD
    0.07
    é«ĺ强
    0.07
    Activations Density 0.001%

    No Known Activations