© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58824
    Prev
    Next
    INDEX
    Explanations

    thin film deposition layers

    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
    äºĶåĽĽ
    -0.07
     ju
    -0.07
    orelease
    -0.07
    纨
    -0.07
    訳
    -0.06
     objections
    -0.06
    æĶ¹ç¼ĸ
    -0.06
    LLU
    -0.06
    Ju
    -0.06
     dere
    -0.06
    POSITIVE LOGITS
     layer
    0.12
     layers
    0.12
    äºĨä¸Ģå±Ĥ
    0.12
    ä¸Ģå±Ĥ
    0.11
    layer
    0.11
    å±Ĥ
    0.11
    Layer
    0.11
    å±ĤçļĦ
    0.11
     deposition
    0.10
     Layer
    0.10
    Activations Density 0.186%

    No Known Activations