© 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. 17638
    Prev
    Next
    INDEX
    Explanations

    member of a subset

    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
    å¾Ģ
    -0.07
    /or
    -0.06
    æĹĹé¼ĵ
    -0.06
    ibert
    -0.06
    ãģĹãĤį
    -0.06
    toon
    -0.06
    åľ¨åı°æ¹¾
    -0.06
    ngle
    -0.06
    å¾Ģå¤į
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    POSITIVE LOGITS
    /out
    0.08
    äºĨä¸ĢèĪ¬
    0.08
    åªĽ
    0.08
     confines
    0.07
    æłĸ
    0.07
    menge
    0.07
     пÑĢеделаÑħ
    0.07
    ë°Ģ
    0.07
     Subset
    0.07
     phạm
    0.07
    Activations Density 0.012%

    No Known Activations