© 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. 47512
    Prev
    Next
    INDEX
    Explanations

    specific code or programming terms

    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
    èĻĶ
    -0.06
    ä¸Ģå±Ģ
    -0.06
    ä¸Ģä¸Ģ
    -0.06
    atters
    -0.06
     terms
    -0.06
    åĨįä¸ī
    -0.06
    :checked
    -0.06
    æ§IJ
    -0.06
    wai
    -0.06
    ump
    -0.06
    POSITIVE LOGITS
    chien
    0.08
    nze
    0.08
    èģªæĺİçļĦ
    0.07
    cpy
    0.07
    ÛķÚ©
    0.07
    _ie
    0.07
    è¿Ļ项
    0.07
    zung
    0.07
    ÑģÑı
    0.07
    reform
    0.07
    Activations Density 0.023%

    No Known Activations