© 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. 26800
    Prev
    Next
    INDEX
    Explanations

    place names with zip codes

    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
    å°Ĩåĩºçİ°
    -0.07
    æij©
    -0.07
    ila
    -0.07
    è¿ĺä¼ļåĩºçİ°
    -0.07
    龸
    -0.07
    ارة
    -0.06
    ำ
    -0.06
    ×Ļת
    -0.06
    jour
    -0.06
    ело
    -0.06
    POSITIVE LOGITS
    亦çĦ¶
    0.07
    åĵ¼åĵ¼
    0.07
    ç½ķ
    0.07
    对记èĢħ
    0.06
     Enhancement
    0.06
    acific
    0.06
    æĻĹ
    0.06
     beli
    0.06
    chied
    0.06
    æīĢå±ŀè¡Įä¸ļ
    0.06
    Activations Density 0.087%

    No Known Activations