© 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. 39867
    Prev
    Next
    INDEX
    Explanations

    code separators

    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
    æµĨ
    -0.06
    ä¸į移
    -0.06
    ä¸į妨
    -0.06
    常ä½ı
    -0.06
    inger
    -0.06
     Ñģобой
    -0.06
    erry
    -0.06
    -0.06
    ä¸Ģéģĵ
    -0.06
     dep
    -0.06
    POSITIVE LOGITS
    omar
    0.08
    ancers
    0.08
    etwork
    0.08
    esor
    0.08
    даÑĤ
    0.08
    isure
    0.08
    uttle
    0.08
    antil
    0.08
    庵
    0.08
    aped
    0.07
    Activations Density 0.023%

    No Known Activations