© 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. 26723
    Prev
    Next
    INDEX
    Explanations

    scale or transform

    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
    zen
    -0.07
    zep
    -0.07
    åģİ
    -0.06
    िश
    -0.06
    ưỡng
    -0.06
    ä»»
    -0.06
    ä¾Ŀ
    -0.06
    æĩ
    -0.06
    Catch
    -0.06
    _CYCLE
    -0.06
    POSITIVE LOGITS
     scaling
    0.10
    scaling
    0.09
     transformation
    0.09
    缩æĶ¾
    0.09
    caling
    0.09
     Scaling
    0.09
     transform
    0.09
     scale
    0.08
    translate
    0.08
    æĺłå°Ħ
    0.08
    Activations Density 0.080%

    No Known Activations