© 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. 42216
    Prev
    Next
    INDEX
    Explanations

    apply filters, Pacific time, https

    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
     éc
    -0.08
    RIPT
    -0.07
    redo
    -0.07
    ذاÙĥ
    -0.07
    icano
    -0.07
    .scan
    -0.07
    loge
    -0.07
     discu
    -0.07
    steen
    -0.07
    ór
    -0.07
    POSITIVE LOGITS
     '
    0.08
    ç°
    0.06
    ither
    0.06
     fores
    0.06
    ｡
    0.06
     **‘
    0.06
    â
    0.06
     '_
    0.06
    楼主
    0.06
    shed
    0.05
    Activations Density 0.011%

    No Known Activations