© 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. 25669
    Prev
    Next
    INDEX
    Explanations

    complex, complicated

    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
    ä¸īå°º
    -0.08
    rup
    -0.07
    reen
    -0.07
     pilo
    -0.06
    çī©çIJĨ
    -0.06
    äuse
    -0.06
     artifact
    -0.06
    INY
    -0.06
    æĤī
    -0.06
    айд
    -0.06
    POSITIVE LOGITS
    å¤įæĿĤ
    0.15
    complex
    0.14
     complex
    0.14
    Complex
    0.13
     komplex
    0.13
    å¤įæĿĤçļĦ
    0.13
     Complex
    0.13
    è¤ĩéĽij
    0.13
    æ¯Ķè¾ĥå¤įæĿĤ
    0.12
     complicated
    0.12
    Activations Density 0.109%

    No Known Activations