© 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. 15819
    Prev
    Next
    INDEX
    Explanations

    saddle point

    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
    eshire
    -0.09
    ¾
    -0.07
    ัà¹Īà¸ĩ
    -0.07
     haus
    -0.07
    åħĨ
    -0.07
    _CHOICES
    -0.07
    æīĢæľª
    -0.07
    /videos
    -0.07
    ä¸¤çľ¼
    -0.07
    /disable
    -0.07
    POSITIVE LOGITS
    zeug
    0.07
    éªĭ
    0.07
    phinx
    0.07
    åĸľéĹ»
    0.07
    -type
    0.06
    港åħĥ
    0.06
    åݲ
    0.06
    vais
    0.06
    edian
    0.06
    udson
    0.06
    Activations Density 0.003%

    No Known Activations