© 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. 10571
    Prev
    Next
    INDEX
    Explanations

    'White', 'promotional', 'as', 'He says', 'could indirectly', 'Imagine'

    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
    æµ·é»ĺ
    -0.09
    è°Īèµ·
    -0.08
    ILING
    -0.07
    edig
    -0.07
    geries
    -0.07
    .onChange
    -0.07
    大åħ¬
    -0.07
    ãĥ¼ãĥĹ
    -0.07
    iling
    -0.07
    ικÏĮÏĤ
    -0.07
    POSITIVE LOGITS
    幸
    0.08
    ait
    0.07
    /ms
    0.06
    ëĭ¥
    0.06
    Ñįг
    0.06
    ä¸ĢåĪĻ
    0.06
    æľīçĪ±
    0.06
    åĽ½åĨħå¤ĸ
    0.06
    ssen
    0.06
    itch
    0.06
    Activations Density 0.005%

    No Known Activations