© 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. 39494
    Prev
    Next
    INDEX
    Explanations

    million, Rene, Kw, Lam, Map

    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
    夥
    -0.07
    ìĦ¼
    -0.07
    篡
    -0.07
    ä¼Ļ
    -0.07
    upa
    -0.06
    omain
    -0.06
    orii
    -0.06
    ä¸įæĢķ
    -0.06
    emp
    -0.06
    åıĪæĪĸèĢħ
    -0.06
    POSITIVE LOGITS
    irmed
    0.07
    reden
    0.07
    kab
    0.07
    ÏĦί
    0.07
    èī¾çijŀ
    0.07
    stown
    0.07
     Azienda
    0.07
     (!((
    0.06
    交çļĦ
    0.06
     elevation
    0.06
    Activations Density 0.017%

    No Known Activations