© 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. 12722
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    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
    ยà¸Ļ
    -0.07
    åĬłæĸ¯
    -0.07
    æĶ¯
    -0.07
    arbon
    -0.07
    íıŃ
    -0.07
    ç«ĭåį³ä¸ĭè½½
    -0.07
    fare
    -0.06
    uka
    -0.06
    æŁ¥çľĭ详ç»Ĩ
    -0.06
    女éĥİ
    -0.06
    POSITIVE LOGITS
    ä½łä¸Ģ个
    0.07
    宽广
    0.07
    anden
    0.07
    èį¸
    0.07
    kins
    0.07
    .python
    0.07
    zing
    0.06
    gest
    0.06
    以赴
    0.06
    åıĺæĢģ
    0.06
    Activations Density 0.040%

    No Known Activations