© 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. 1264
    Prev
    Next
    INDEX
    Explanations

    node, mathematical expressions, or code components

    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
    ëĮĢë¡ľ
    -0.07
    ä¹¾åĿ¤
    -0.07
    åıĸéķ¿è¡¥çŁŃ
    -0.06
    etan
    -0.06
    天ä¸Ĭ
    -0.06
    óta
    -0.06
    åįķä½įåĴĮ个人
    -0.06
    çķ
    -0.06
    -order
    -0.06
    主è¦ģéĽĨä¸Ńåľ¨
    -0.06
    POSITIVE LOGITS
    èĬĤçĤ¹çļĦ
    0.09
    verso
    0.09
    node
    0.09
    usher
    0.09
     node
    0.08
    _NODE
    0.08
    nodeName
    0.08
    ç»ĵçĤ¹
    0.08
    èĬĤçĤ¹
    0.08
     nodeName
    0.08
    Activations Density 0.004%

    No Known Activations