© 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. 22950
    Prev
    Next
    INDEX
    Explanations

    programming nouns or technical terms

    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
    ksom
    -0.06
    zes
    -0.06
     Siri
    -0.05
    almente
    -0.05
    äºļäºİ
    -0.05
    .deepEqual
    -0.05
    tt
    -0.05
    teile
    -0.05
    ineTransform
    -0.05
     phú
    -0.05
    POSITIVE LOGITS
    /../
    0.08
    otine
    0.08
    worthy
    0.08
    ìĩ¼
    0.08
    adays
    0.08
    ellaneous
    0.08
    lod
    0.07
    <tool_response>
    0.07
    bidden
    0.07
    ocoa
    0.07
    Activations Density 0.520%

    No Known Activations