© 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. 19943
    Prev
    Next
    INDEX
    Explanations

    filing documents

    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
    Ð¢Ðł
    -0.08
    arius
    -0.07
    ifact
    -0.07
    ooth
    -0.07
    [âĢ¦]
    -0.07
    archy
    -0.07
    çļĦèĥĮå½±
    -0.07
    åŀ¢
    -0.07
    å·¥ä¸ļåĩºçīĪ社
    -0.07
    isser
    -0.07
    POSITIVE LOGITS
    éĥİ
    0.07
    eni
    0.07
    amaz
    0.07
    enia
    0.07
    à¹Īà¸ĩ
    0.07
    Ī
    0.07
    lean
    0.06
    çĽĪ
    0.06
    ená
    0.06
    åı¯ä»¥çIJĨ解
    0.06
    Activations Density 0.135%

    No Known Activations