© 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. 56847
    Prev
    Next
    INDEX
    Explanations

    analogy or similarity

    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
    ereo
    -0.07
    usso
    -0.07
    ë³µ
    -0.07
    isol
    -0.07
    anske
    -0.07
    å¦ŀ
    -0.06
    çĤºä¸»
    -0.06
    æŁ¥çľĭ详ç»Ĩ
    -0.06
    voli
    -0.06
    èĤ©éĥ¨
    -0.06
    POSITIVE LOGITS
     analogous
    0.14
    类似çļĦ
    0.13
     analogy
    0.12
     Analog
    0.11
     similarly
    0.11
    ç±»æ¯Ķ
    0.11
    类似
    0.11
    ä¹ĭäºİ
    0.10
     analog
    0.10
    ç±»æݨ
    0.10
    Activations Density 0.314%

    No Known Activations