© 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. 2849
    Prev
    Next
    INDEX
    Explanations

    preceding or earlier

    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
    ä»ĸ羣çļĦ
    -0.08
    æ±Ĥ羣åĬ¡å®ŀ
    -0.08
     dicip
    -0.08
    rowse
    -0.08
    ç¬ijèµ·æĿ¥
    -0.08
    estat
    -0.08
     fotograf
    -0.07
    ç¬ijèijĹ
    -0.07
    ì³
    -0.07
    оÑĩе
    -0.07
    POSITIVE LOGITS
     preceding
    0.07
     earlier
    0.07
    éĻĦ带
    0.07
     preced
    0.07
    iram
    0.06
    ç´§æİ¥çĿĢ
    0.06
     précéd
    0.06
    eben
    0.06
    åīįéĿ¢çļĦ
    0.06
     part
    0.06
    Activations Density 0.009%

    No Known Activations