© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    code structure and symbols

    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
    -0.07
    为ä¸Ģ
    -0.06
     p
    -0.06
     numeric
    -0.06
    поÑĢ
    -0.06
     ten
    -0.06
    P
    -0.06
    为人
    -0.06
    M
    -0.05
    p
    -0.05
    POSITIVE LOGITS
    å¿ĺä¸įäºĨ
    0.09
     Ilmais
    0.09
    togroup
    0.09
    ози
    0.08
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    0.08
    å¦Ĥæľīä¾µæĿĥ
    0.08
    ’B
    0.08
    afil
    0.08
     побÑĥ
    0.08
    /mit
    0.08
    Activations Density 0.003%

    No Known Activations