© 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. 31528
    Prev
    Next
    INDEX
    Explanations

    legal citations and structured text

    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
    èĨ
    -0.06
    åįģä¸Ģ
    -0.06
    ç»Īäºİ
    -0.06
    ç»Ī
    -0.06
    æĸĩ件精ç¥ŀ
    -0.06
    éĵ¿
    -0.06
    ents
    -0.06
    广
    -0.06
     gross
    -0.06
    第åįģä¸Ģ
    -0.06
    POSITIVE LOGITS
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    0.09
    WithString
    0.08
    aguay
    0.08
    lias
    0.07
     Jaya
    0.07
    åıijè¡¨åľ¨
    0.07
    ucu
    0.07
    aque
    0.07
    ç®Ģç®Ģåįķ
    0.07
    Scrollbar
    0.07
    Activations Density 0.005%

    No Known Activations