© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    programmatic concepts

    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
    طب
    -0.07
    oth
    -0.07
    éĿ
    -0.07
    (ep
    -0.06
    rame
    -0.06
    æīĢåѦä¸ĵä¸ļ
    -0.06
    Ø«ÙĨ
    -0.06
    emez
    -0.06
    heck
    -0.06
    erc
    -0.06
    POSITIVE LOGITS
     anyway
    0.07
    alic
    0.07
     justamente
    0.07
    å°±æĺ¯è¿Ļ个
    0.07
    åĩºä¸Ģçīĩ
    0.07
    åıªå¾Ĺ
    0.07
     ugy
    0.07
     vén
    0.07
     hacked
    0.07
    utsch
    0.06
    Activations Density 0.045%

    No Known Activations