© 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. 23367
    Prev
    Next
    INDEX
    Explanations

    hybridization, epithelial cells, Macedonian

    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
    æīĢå¤Ħ
    -0.07
     Finch
    -0.07
    atten
    -0.07
    rch
    -0.06
    æīĢåľ¨åľ°
    -0.06
    EXPR
    -0.06
    çħŀ
    -0.06
    elder
    -0.06
    _spawn
    -0.06
    istor
    -0.06
    POSITIVE LOGITS
    çī¹åĪ«æĺ¯
    0.10
    ç±»åŀĭ
    0.09
    ç±»åŀĭ为
    0.09
    é¡ŀåŀĭ
    0.09
    å°¤åħ¶æĺ¯
    0.09
    é¡ŀ
    0.09
     types
    0.09
     ÑĤипа
    0.09
     Types
    0.09
     type
    0.08
    Activations Density 1.413%

    No Known Activations