© 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. 13532
    Prev
    Next
    INDEX
    Explanations

    long descriptive words

    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
    æķħéĩĮ
    -0.07
    orse
    -0.06
    andid
    -0.06
    缸åħ³ä¿¡æģ¯
    -0.06
    pond
    -0.06
    contri
    -0.06
    æ¢ĵ
    -0.06
    æ¥ļæ¥ļ
    -0.06
    夫
    -0.06
    ecret
    -0.05
    POSITIVE LOGITS
    çļĦéĤ£ä¸ª
    0.10
     kia
    0.10
    çļĦéĤ£ä¸Ģ天
    0.08
    _eof
    0.08
    utenberg
    0.08
    -Apr
    0.07
     genannten
    0.07
    çļĦéĤ£å¤©
    0.07
     kyn
    0.07
    ä¸Ģ个å¤ļæľĪ
    0.07
    Activations Density 0.118%

    No Known Activations