© 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. 13426
    Prev
    Next
    INDEX
    Explanations

    Mon–Fri

    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
    chin
    -0.06
     Nesta
    -0.06
    auh
    -0.06
    ijkstra
    -0.06
    anda
    -0.06
    èµ°äºĨ
    -0.06
    صاب
    -0.06
    inator
    -0.06
    ossa
    -0.06
    dav
    -0.06
    POSITIVE LOGITS
    ä¸Ģèĩ³
    0.14
    ä¸Ģ缴åĪ°
    0.14
    ë¶ĢíĦ°
    0.13
    以éĻį
    0.13
    缴èĩ³
    0.13
    èĩ³
    0.13
    以èĩ³
    0.12
    à¸Īà¸Ļà¸ĸึà¸ĩ
    0.12
     až
    0.12
    æĹ¥èĩ³
    0.11
    Activations Density 0.359%

    No Known Activations