© 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. 15338
    Prev
    Next
    INDEX
    Explanations

    layout 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
     напиÑģ
    -0.07
    ffield
    -0.07
    cak
    -0.07
    ä¸Ģç»ıåıijçİ°
    -0.07
    åĵģçīĮ形象
    -0.07
    è¿ŀéĶģåºĹ
    -0.07
    家éŨåı£
    -0.06
    æĢİä¹ĪåĨĻ
    -0.06
    isen
    -0.06
    .getState
    -0.06
    POSITIVE LOGITS
     distribute
    0.09
     Distrib
    0.09
     distributing
    0.09
     distributes
    0.08
    å¸ĥå±Ģ
    0.08
    横åIJij
    0.08
    .Layout
    0.08
    layout
    0.08
     Layout
    0.08
     Distribution
    0.08
    Activations Density 0.113%

    No Known Activations