© 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. 18748
    Prev
    Next
    INDEX
    Explanations

    codes and labels like `var1`

    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
    两人çļĦ
    -0.08
    vg
    -0.07
    ä¸¤äººåľ¨
    -0.07
    ayu
    -0.07
    ivity
    -0.07
    ol
    -0.07
    ivism
    -0.07
    两个人çļĦ
    -0.07
     both
    -0.06
    åħ©äºº
    -0.06
    POSITIVE LOGITS
    æķ°çĽ®
    0.09
    nds
    0.09
    çļĦéĤ£äºĽ
    0.08
     ÐŁÐ¾Ñģледние
    0.08
    第ä¸Ģæī¹
    0.08
     berjumlah
    0.08
    è¡¥åħħ
    0.08
     outnumber
    0.08
    åı¦ä¸ĢåįĬ
    0.08
     denen
    0.08
    Activations Density 0.126%

    No Known Activations