© 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. 57184
    Prev
    Next
    INDEX
    Explanations

    addition and transition 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
    ervi
    -0.07
     Berb
    -0.07
    erva
    -0.07
    inea
    -0.07
    idr
    -0.07
    注åĨĮèµĦæľ¬ä¸º
    -0.07
    yre
    -0.07
    大路
    -0.06
    erc
    -0.06
    ört
    -0.06
    POSITIVE LOGITS
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.09
    åIJĮæĹ¶å¯¹
    0.08
     subsequently
    0.08
    åIJĮæĻĤ
    0.08
    ogh
    0.08
     anschlieÃŁend
    0.08
    åIJĮæĹ¶åľ¨
    0.07
     afterward
    0.07
    åIJĮæĻĤãģ«
    0.07
    åIJĮæŶè¿ĺ
    0.07
    Activations Density 0.192%

    No Known Activations