© 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
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48466
    Prev
    Next
    INDEX
    Explanations

    data encoding or serialization

    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
    fore
    -0.07
    oire
    -0.07
    phone
    -0.07
    _OWNER
    -0.07
    olithic
    -0.07
    mount
    -0.07
    uve
    -0.07
    avera
    -0.07
    èݽ
    -0.07
    ud
    -0.07
    POSITIVE LOGITS
    åĽ½éĻħä¼ļå±ķä¸Ńå¿ĥ
    0.07
    assage
    0.07
    çĸı
    0.07
    ä¸Ń以
    0.07
    iami
    0.07
    .dumps
    0.07
    Inspectable
    0.07
    ÃŃch
    0.07
    dash
    0.07
    ä¸ŃåIJ«
    0.06
    Activations Density 0.006%

    No Known Activations