© 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. 13862
    Prev
    Next
    INDEX
    Explanations

    boundary condition

    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
    νÏĮ
    -0.08
    亿人æ°ijå¸ģ
    -0.08
    leur
    -0.07
    inet
    -0.07
    otify
    -0.07
    å±ħæĺĵ
    -0.07
    娶
    -0.07
    imbau
    -0.07
    zinho
    -0.07
     rall
    -0.07
    POSITIVE LOGITS
    æĮĩå®ļçļĦ
    0.09
    约æĿŁ
    0.09
     imposed
    0.09
    æĮĩå®ļ
    0.08
     constraints
    0.08
     specifying
    0.08
    è¦ģæ±Ĥåľ¨
    0.08
     contorno
    0.07
    spf
    0.07
    constraints
    0.07
    Activations Density 0.011%

    No Known Activations