© 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. 29761
    Prev
    Next
    INDEX
    Explanations

    available information

    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
    ibar
    -0.08
     triá»ģu
    -0.08
    echa
    -0.07
    çĭ
    -0.07
    建工
    -0.07
    è¿ĺæĮº
    -0.07
     Ramp
    -0.07
    stown
    -0.07
     заÑģÑĤо
    -0.07
    \\/
    -0.07
    POSITIVE LOGITS
     ter
    0.07
    ter
    0.06
    plete
    0.06
    atted
    0.06
    ìŀ¥ìĿĢ
    0.06
     commence
    0.06
    åħĪ
    0.06
    åı¦å¤ĸä¸Ģ个
    0.06
    åıij表äºİ
    0.06
    å¼Ģå§ĭåīį
    0.06
    Activations Density 0.013%

    No Known Activations