© 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. 43922
    Prev
    Next
    INDEX
    Explanations

    temporary

    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
    er
    -0.10
    ersten
    -0.08
    ermann
    -0.08
    äºĨ对
    -0.08
    ered
    -0.08
    s
    -0.08
    erma
    -0.08
    hood
    -0.07
    داء
    -0.07
    emberg
    -0.07
    POSITIVE LOGITS
    orarily
    0.13
    orary
    0.12
    inals
    0.09
    ëĿ¼ëıĦ
    0.08
    resident
    0.08
    oral
    0.08
    ixels
    0.08
    èİ«åıĬ
    0.08
    EDIATE
    0.08
    unen
    0.07
    Activations Density 0.025%

    No Known Activations