© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16276
    Prev
    Next
    INDEX
    Explanations

    email addresses and numbers ending in k

    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
    cito
    -0.07
    ércoles
    -0.07
    /she
    -0.07
    åĴĮ好
    -0.06
    .ie
    -0.06
    aussian
    -0.06
    åIJĦéĥ¨
    -0.06
    èijĨ
    -0.06
    -*-
    -0.06
    ENTS
    -0.06
    POSITIVE LOGITS
    åı·éĻ¢
    0.08
    arana
    0.07
    ีม
    0.07
    _asc
    0.07
    erty
    0.07
    ä¸Ģ书
    0.07
    ÙıÙħÙİÙij
    0.07
    kehr
    0.07
     renamed
    0.06
    peat
    0.06
    Activations Density 0.116%

    No Known Activations