© 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. 2789
    Prev
    Next
    INDEX
    Explanations

    add ingredients

    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
    lav
    -0.07
    omt
    -0.07
    人æ°ij群ä¼ĹçļĦ
    -0.07
    SPA
    -0.07
    ersh
    -0.07
    isclosed
    -0.06
    liv
    -0.06
    otov
    -0.06
    çı¾åľ¨ãģ¯
    -0.06
    omb
    -0.06
    POSITIVE LOGITS
    ä¸Ģèµ·åŃ¦ä¹ł
    0.08
     hinzu
    0.08
     stir
    0.07
    åħ¨éĥ¨åĨħ容
    0.07
    éĤ£é¢Ĺ
    0.07
    åľ¨éĩĮéĿ¢
    0.07
    atoire
    0.07
    ENTA
    0.07
     Sat
    0.07
     Konkurre
    0.07
    Activations Density 0.024%

    No Known Activations