© 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. 17959
    Prev
    Next
    INDEX
    Explanations

    diagrams or images below

    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
    åįģäºĮç«ł
    -0.08
    çĤī
    -0.08
    æľ¬æłĩåĩĨ
    -0.08
    okit
    -0.08
    åħ¬åı¸åIJij
    -0.07
    DDS
    -0.07
    宫é¢Īç³ľçĥĤ
    -0.07
    ÙĬاج
    -0.07
     Viol
    -0.07
    {text
    -0.07
    POSITIVE LOGITS
    éĽ¹
    0.06
    注
    0.06
    ä¸Ģé¡¿
    0.06
    çĤ¹åĩ»åĽ¾çīĩ
    0.06
     sortable
    0.06
    egu
    0.06
    kur
    0.06
     Konk
    0.06
     incarcer
    0.06
    ä¸ĬåĽ¾
    0.06
    Activations Density 0.482%

    No Known Activations