© 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. 64481
    Prev
    Next
    INDEX
    Explanations

    coat or primer

    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
    edt
    -0.07
    yled
    -0.06
    beck
    -0.06
    leder
    -0.06
    lage
    -0.06
    illet
    -0.06
    è¿·æĥij
    -0.06
     Steering
    -0.06
    ile
    -0.06
    _since
    -0.06
    POSITIVE LOGITS
    ä¸Ģéģį
    0.09
     afterward
    0.09
    .before
    0.08
    è¿Ľä¸ĢæŃ¥å¼ºåĮĸ
    0.08
    äºĨä¸Ģéģį
    0.08
     strengthens
    0.08
    波士
    0.08
     dilanjutkan
    0.08
    jú
    0.08
    _before
    0.08
    Activations Density 0.025%

    No Known Activations