© 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. 60288
    Prev
    Next
    INDEX
    Explanations

    hundred-fold

    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
    incer
    -0.07
    d
    -0.06
    iece
    -0.06
    opes
    -0.06
     cap
    -0.06
    ãĤĦãģĹ
    -0.06
    ÑĦов
    -0.06
    oc
    -0.06
    人åIJį
    -0.06
    ical
    -0.06
    POSITIVE LOGITS
    -scrollbar
    0.09
    uye
    0.08
    -suite
    0.08
    /gcc
    0.08
    رد
    0.08
    unan
    0.07
     sekal
    0.07
    /template
    0.07
    £¼
    0.07
    èĢĺ
    0.07
    Activations Density 0.012%

    No Known Activations