© 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. 26091
    Prev
    Next
    INDEX
    Explanations

    fixed point propagation plane

    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
     Morales
    -0.07
    åĬłå·¥
    -0.07
    urian
    -0.07
    ä¸Ģè·¯
    -0.07
     íĵ¨
    -0.07
     anthrop
    -0.07
    urig
    -0.07
     defs
    -0.07
    縫
    -0.06
    éĿŀ常æĸ¹ä¾¿
    -0.06
    POSITIVE LOGITS
    usher
    0.08
    wor
    0.07
     Boyd
    0.07
    opup
    0.07
    wave
    0.07
    éĿłå±±
    0.07
     McKenzie
    0.07
    ikh
    0.06
     sach
    0.06
    Pk
    0.06
    Activations Density 0.003%

    No Known Activations