© 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. 49056
    Prev
    Next
    INDEX
    Explanations

    extending upward or downward

    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
    celer
    -0.07
     Vand
    -0.07
    emos
    -0.07
    Spot
    -0.07
     ذات
    -0.07
    åıĪä¸Ģ次
    -0.06
    ievi
    -0.06
    isu
    -0.06
    URN
    -0.06
     lót
    -0.06
    POSITIVE LOGITS
    延伸èĩ³
    0.17
    延伸
    0.16
    延伸åĪ°
    0.16
     beyond
    0.14
     extends
    0.12
     Beyond
    0.12
    extends
    0.12
    Beyond
    0.12
     extending
    0.11
     extend
    0.11
    Activations Density 0.135%

    No Known Activations