© 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. 22051
    Prev
    Next
    INDEX
    Explanations

    Peyton

    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
    aday
    -0.08
    artig
    -0.06
    åħ®
    -0.06
    irsch
    -0.06
    éĿŀåħ¬
    -0.06
    agri
    -0.06
    urr
    -0.06
    éķ¿çĽ¸
    -0.06
    æľīçIJĨ
    -0.06
    åĨį好
    -0.06
    POSITIVE LOGITS
    æĪijçļĦå¿ĥéĩĮ
    0.08
    %E
    0.07
    zd
    0.07
    taler
    0.07
    ony
    0.07
     embr
    0.07
     Verteid
    0.07
    abwe
    0.07
    ITI
    0.07
    _modifier
    0.07
    Activations Density 0.027%

    No Known Activations