© 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. 31358
    Prev
    Next
    INDEX
    Explanations

    matrix dimensions and shapes

    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
    hely
    -0.07
    认
    -0.07
    vos
    -0.07
    halt
    -0.07
    ecip
    -0.06
    æī¬å¸Ĩ
    -0.06
     constituents
    -0.06
    åħ¥æĪ·
    -0.06
    åīĤçļĦ
    -0.06
    leps
    -0.06
    POSITIVE LOGITS
    ieden
    0.08
    ibat
    0.08
    å¤ļæľĪ
    0.07
    ëŀŃ
    0.07
    panse
    0.07
    arien
    0.07
     Colo
    0.07
    rank
    0.07
    åĽŀçŃĶéĩı
    0.07
    èªĩãĤĭ
    0.07
    Activations Density 0.008%

    No Known Activations