© 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. 48852
    Prev
    Next
    INDEX
    Explanations

    upgrade, swelling, second, keyword

    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
    Âł
    -0.07
    -0.06
    dress
    -0.06
    ãĢħ
    -0.06
    åĩ¡æĺ¯
    -0.05
    (:
    -0.05
     Matters
    -0.05
    adat
    -0.05
    å°ıäºĭ
    -0.05
     as
    -0.05
    POSITIVE LOGITS
    ä»ħéĻIJäºİ
    0.10
    ãģĤãģı
    0.10
    åģļçļĦæĺ¯
    0.09
    ä¸įæĺ¯æĪij
    0.09
    ä»ħéĻIJ
    0.09
    weiler
    0.09
    alni
    0.08
     Ø¥ÙĨÙħا
    0.08
    ÙĦÙĬÙĥ
    0.08
    aliza
    0.08
    Activations Density 0.238%

    No Known Activations