© 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. 38927
    Prev
    Next
    INDEX
    Explanations

    variables and identifiers

    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
    ↵
    -0.06
    è£
    -0.06
    磨
    -0.06
    æ¡IJ
    -0.06
    éĢ
    -0.06
     loc
    -0.06
     gr
    -0.06
    éĩıçļĦ
    -0.06
    åIJĽåŃIJ
    -0.06
      ↵
    -0.05
    POSITIVE LOGITS
    ãĤıãĤĬãģ«
    0.08
    æĪij以
    0.08
    amiÄĻ
    0.08
     eksk
    0.08
    /Branch
    0.08
     Casas
    0.08
    iette
    0.08
    ixo
    0.08
    ½ij
    0.07
    ¤íĮ
    0.07
    Activations Density 0.048%

    No Known Activations