© 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. 41646
    Prev
    Next
    INDEX
    Explanations

    belongs to

    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
    è¿Ļæĺ¯æĪij
    -0.07
    ypo
    -0.07
    umb
    -0.06
     Harr
    -0.06
     c
    -0.06
    æļ¦
    -0.06
    -cols
    -0.06
     phó
    -0.06
    à¹Ģà¸ļืà¹īà¸Ńà¸ĩ
    -0.06
    ornos
    -0.06
    POSITIVE LOGITS
     belongs
    0.14
     belonged
    0.14
    å½Ĵå±ŀäºİ
    0.13
    éļ¶å±ŀäºİ
    0.13
     belong
    0.12
    belongs
    0.12
    æīĢåľ¨çļĦ
    0.12
    å½Ĵå±ŀ
    0.11
    æīĢå±ŀ
    0.11
     pertenece
    0.11
    Activations Density 0.210%

    No Known Activations