© 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. 28390
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis after 'right'

    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
    wear
    -0.07
    ikk
    -0.07
    bruck
    -0.07
    åħĪçĶŁè¯´
    -0.07
    ай
    -0.07
    æĥħåĨµçŃī
    -0.07
    غار
    -0.07
    åģļçļĦå°±æĺ¯
    -0.07
    lick
    -0.07
    {|
    -0.07
    POSITIVE LOGITS
    åľ¨
    0.12
    缸è¾ħ缸æĪIJ
    0.10
    çļĦ
    0.10
    ãĢģ“
    0.08
    俱ä¹IJéĥ¨
    0.08
    ł
    0.08
    ×ķת
    0.08
    ï¸ı
    0.07
    orary
    0.07
    ãĢģãĢİ
    0.07
    Activations Density 0.005%

    No Known Activations