© 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. 30593
    Prev
    Next
    INDEX
    Explanations

    invention relates

    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
    gles
    -0.07
     VOC
    -0.07
    èĪĮå°ĸ
    -0.07
     api
    -0.07
    ä»·åĢ¼éĵ¾
    -0.06
    ä¸Ģè¨Ģ
    -0.06
    곤
    -0.06
    éĹ¯
    -0.06
    跳跳
    -0.06
     API
    -0.06
    POSITIVE LOGITS
    ç¼łç»ķ
    0.07
    æł¸çĶµ
    0.07
    _AXIS
    0.07
    edar
    0.07
    ç¿Ĵ
    0.07
    楷
    0.07
    亥
    0.07
     rehears
    0.07
    Fd
    0.07
    dir
    0.07
    Activations Density 0.005%

    No Known Activations