© 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. 12869
    Prev
    Next
    INDEX
    Explanations

    direction or reversal

    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
    addAll
    -0.07
    æ·¡
    -0.06
    ä¹ĭç¥ŀ
    -0.06
    ethereum
    -0.06
     &,
    -0.06
    ÏĦιά
    -0.06
     construct
    -0.06
    èĮħ
    -0.06
    atico
    -0.06
    åı°
    -0.06
    POSITIVE LOGITS
    åıįä¹ĭ
    0.09
    缸åıįçļĦ
    0.09
     reversing
    0.09
    åıį转
    0.09
     sebaliknya
    0.09
     reverse
    0.08
     reversal
    0.08
    åıįè¿ĩæĿ¥
    0.08
     aÃŃ
    0.08
     Kut
    0.08
    Activations Density 0.011%

    No Known Activations