© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10667
    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
    headed
    -0.08
    头æĿ¡
    -0.08
    æijĩäºĨ
    -0.07
     headed
    -0.07
    æī¬éķ¿
    -0.07
     clar
    -0.07
    serde
    -0.07
    arczy
    -0.07
    моÑĤ
    -0.07
    unicode
    -0.07
    POSITIVE LOGITS
    inke
    0.08
    约æĿŁ
    0.08
    estruc
    0.07
     Brug
    0.07
     constraint
    0.07
    Unused
    0.07
    没è¿ĩ
    0.07
    apur
    0.07
    第åįģä¸ĥ
    0.07
     endure
    0.07
    Activations Density 0.003%

    No Known Activations