© 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. 24726
    Prev
    Next
    INDEX
    Explanations

    origin (0,0)

    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
    -wise
    -0.07
    elui
    -0.07
    uzzi
    -0.07
    ì¤Ħ
    -0.07
    ately
    -0.07
    rella
    -0.06
     Sheridan
    -0.06
    ennial
    -0.06
    迪æĸ¯
    -0.06
    æ²¹çĽIJ
    -0.06
    POSITIVE LOGITS
    ยิà¸Ļ
    0.08
    chenk
    0.08
    CKET
    0.07
     ÙĪØ¥ÙĦÙī
    0.07
    éĥ½ä¸įè¦ģ
    0.07
    é¾Ħ
    0.07
    chutz
    0.07
    angat
    0.07
     Jako
    0.07
     menemp
    0.06
    Activations Density 0.003%

    No Known Activations