© 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. 57541
    Prev
    Next
    INDEX
    Explanations

    non-English word parts and suffixes

    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
    ¶
    -0.06
    ình
    -0.06
    onto
    -0.06
    anker
    -0.06
     pigeon
    -0.06
     Succ
    -0.06
    ä¹İ
    -0.06
    Compact
    -0.06
     Fork
    -0.06
    令æĪij
    -0.06
    POSITIVE LOGITS
    æłijä¸Ģ
    0.08
    baum
    0.08
    麻麻
    0.07
    vani
    0.07
    å¿ĥæĤ¦
    0.07
    antor
    0.07
    LOUR
    0.07
    оÑħÑĢани
    0.07
    _ini
    0.07
    èı²å°Ķå¾·
    0.07
    Activations Density 0.417%

    No Known Activations