© 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. 41717
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and specific groups

    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
    gew
    -0.08
    ">'.
    -0.08
    <?>>
    -0.08
    ovo
    -0.08
    erseits
    -0.07
    .hist
    -0.07
    haupt
    -0.07
     Tumblr
    -0.07
    meer
    -0.07
    æħ°
    -0.07
    POSITIVE LOGITS
     described
    0.07
    ãģ¨åij¼ãģ°ãĤĮãĤĭ
    0.07
    æĮīçħ§
    0.06
    ä¸ī段
    0.06
    aid
    0.06
    ï¼Ī
    0.06
    ä¹ĭ称çļĦ
    0.06
     Curt
    0.06
    ä½ľ
    0.06
    âĦ¢
    0.06
    Activations Density 0.484%

    No Known Activations