© 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. 34426
    Prev
    Next
    INDEX
    Explanations

    Chinese characters and system paths

    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»
    -0.07
    ths
    -0.07
    _normalized
    -0.07
    .SqlClient
    -0.07
    elin
    -0.07
    å¨ĵ
    -0.07
    >[]
    -0.07
    ÙĦد
    -0.07
    ило
    -0.07
    _languages
    -0.07
    POSITIVE LOGITS
     brows
    0.07
    atomy
    0.07
    ustom
    0.07
    ancouver
    0.06
    èķĥ
    0.06
    æıĸ
    0.06
    å³°
    0.06
    ä¿ł
    0.06
    漪
    0.06
    ä¾łå®¢
    0.06
    Activations Density 0.001%

    No Known Activations