© 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. 26010
    Prev
    Next
    INDEX
    Explanations

    geometry and shape intersections

    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
    éĿ¢ç§¯
    -0.09
    æĢ»éĿ¢ç§¯
    -0.08
    angkan
    -0.08
    åĬĽä½ľ
    -0.07
    æĴķè£Ĥ
    -0.07
    éĿ¢ç©į
    -0.07
    ä¸Ģçīĩçīĩ
    -0.07
    大çīĩ
    -0.07
    _INITIALIZER
    -0.07
    çīĩçīĩ
    -0.07
    POSITIVE LOGITS
    itom
    0.08
    轴线
    0.08
    enni
    0.08
    egment
    0.08
    bundle
    0.07
    综
    0.07
    两段
    0.07
     Thread
    0.07
    è¿ĩéķ¿
    0.07
    æĺ¯ä¸Ģ段
    0.07
    Activations Density 0.005%

    No Known Activations