© 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. 16909
    Prev
    Next
    INDEX
    Explanations

    trailing slash or zeros

    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
    ['__
    -0.08
     uncont
    -0.08
    ¦
    -0.08
    çģµ
    -0.08
    lotte
    -0.08
    åĬłå¿«
    -0.08
    åIJĮæ¯Ķä¸Ĭåįĩ
    -0.08
    getCell
    -0.07
     Vance
    -0.07
    æķ£
    -0.07
    POSITIVE LOGITS
    çī¹æĦı
    0.07
    强è°ĥäºĨ
    0.07
    stat
    0.07
    +xml
    0.07
     significance
    0.06
    illard
    0.06
    以示
    0.06
     explicitly
    0.06
    /stat
    0.06
    çļĦæĦıä¹ī
    0.06
    Activations Density 0.001%

    No Known Activations