© 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. 13723
    Prev
    Next
    INDEX
    Explanations

    `/` followed by `_` or `2`

    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
    翱
    -0.07
    uran
    -0.07
    ÑĢма
    -0.07
    éĥ½æĺ¯æľī
    -0.06
    ابة
    -0.06
    ARING
    -0.06
    à¥Ĥप
    -0.06
    橱
    -0.06
    _REFER
    -0.06
    wany
    -0.06
    POSITIVE LOGITS
    ÐĶС
    0.08
     Ramp
    0.08
    iose
    0.08
    yss
    0.07
    ило
    0.07
    leit
    0.07
    chron
    0.07
    kontakte
    0.07
    bast
    0.07
    зÑı
    0.06
    Activations Density 0.018%

    No Known Activations