© 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. 55875
    Prev
    Next
    INDEX
    Explanations

    distributed Version

    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
    Ùĩ
    -0.15
    ↵  ↵
    -0.11
    ↵	↵
    -0.11
    ↵ ↵
    -0.11
    ↵   ↵
    -0.10
    ↵     ↵
    -0.10
    ↵    ↵
    -0.10
    ↵		↵
    -0.10
    ↵      ↵
    -0.09
    ↵                        ↵
    -0.09
    POSITIVE LOGITS
    <|box_end|>
    0.12
    ãĢģ“
    0.12
    Ø©
    0.11
    翼翼
    0.09
    ãĢģãĢĮ
    0.09
    /'
    0.09
    и
    0.09
    ãĢģãĢİ
    0.09
    ovah
    0.09
    -même
    0.08
    Activations Density 1.398%

    No Known Activations