© 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. 37827
    Prev
    Next
    INDEX
    Explanations

    sentence endings with conjunctions

    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
    ona
    -0.07
    åıĤ
    -0.06
    áĥ¦
    -0.06
    æ¾ľ
    -0.06
    åIJ§
    -0.06
    lotte
    -0.06
    禧
    -0.06
    ãĥ©ãĤ¤ãĥĪ
    -0.06
    åĴ³åĴ³
    -0.06
    бо
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Ł
    0.07
     inilah
    0.07
    èĢĮèµ°
    0.07
    jec
    0.07
     vle
    0.07
    ç¿ģ
    0.07
    óst
    0.07
    éļ¾æĢª
    0.07
    使ä»ĸ
    0.06
    stras
    0.06
    Activations Density 0.008%

    No Known Activations