© 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. 29289
    Prev
    Next
    INDEX
    Explanations

    German compound nouns

    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
     seques
    -0.08
    ovor
    -0.08
     perpetr
    -0.08
    æľ¬åŃ£
    -0.08
    åºĥåijĬãģ¯
    -0.07
    çĿĢèĦ¸
    -0.07
    ebre
    -0.07
    好åIJ¬
    -0.07
     impecc
    -0.07
    Tracker
    -0.07
    POSITIVE LOGITS
     (âĢŀ
    0.11
     âĢŀ
    0.10
     (=
    0.08
    Nr
    0.08
     der
    0.07
     ü
    0.07
    âĢŀ
    0.07
    -/
    0.07
     kem
    0.07
    ÂŃ
    0.07
    Activations Density 0.263%

    No Known Activations