© 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. 19552
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æķħéĩĮ
    -0.06
     Griff
    -0.06
    pp
    -0.06
     granny
    -0.06
     lined
    -0.06
    é¼İ
    -0.06
    çĤ³
    -0.06
    çĶŁåľ°
    -0.06
    è¨Ī
    -0.06
    ppen
    -0.06
    POSITIVE LOGITS
    ató
    0.08
    AZE
    0.07
    TML
    0.07
    ächt
    0.07
    snake
    0.07
    VML
    0.07
    è¹Ī
    0.07
    uah
    0.07
    æĪ°åł´
    0.07
    /feed
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.