© 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. 41823
    Prev
    Next
    INDEX
    Explanations

    neural networks

    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
    entin
    -0.06
    ä¸Ńèĭ±
    -0.06
    fullscreen
    -0.06
    uhl
    -0.06
    -
    -0.06
    KeyPress
    -0.05
     BST
    -0.05
    åĬªåĬĽ
    -0.05
    -0.05
    ç¹Ķ
    -0.05
    POSITIVE LOGITS
    ifact
    0.08
    òi
    0.08
    ếm
    0.08
    пÑĢом
    0.08
    è§ģéĻĦ件
    0.08
    ẩm
    0.08
    yš
    0.08
    umpang
    0.08
    ventario
    0.08
     Camere
    0.07
    Activations Density 0.632%

    No Known Activations