© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4776
    Prev
    Next
    INDEX
    Explanations

    developer or position

    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
    Negative Logits
    A
    -0.06
    ool
    -0.06
    ients
    -0.06
    2
    -0.06
    F
    -0.06
    ury
    -0.06
    T
    -0.06
    E
    -0.06
    S
    -0.06
    ~
    -0.06
    POSITIVE LOGITS
    对éĤ£äºĽ
    0.09
    asilan
    0.08
    Lorem
    0.08
    toral
    0.08
    <small
    0.08
    prat
    0.08
    åħ¢åħ¢ä¸ļä¸ļ
    0.08
    ompiler
    0.08
    formatter
    0.08
    ependency
    0.08
    Activations Density 0.012%

    No Known Activations