© 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. 58697
    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
    antum
    -0.10
    oric
    -0.08
    çĥŃéŨæłĩçŃ¾
    -0.08
     hiá»ĩp
    -0.07
    è¿ĻäºĽä¸ľè¥¿
    -0.07
    جاÙĨ
    -0.07
    odom
    -0.07
    acus
    -0.07
    atang
    -0.07
    oning
    -0.07
    POSITIVE LOGITS
    .populate
    0.06
    åĬ
    0.06
    ä¸į让
    0.06
    ullet
    0.06
     ob
    0.06
    enzi
    0.06
    çIJ
    0.06
    åħ±åIJĮæݢ讨
    0.06
     Reit
    0.06
     le
    0.06
    Activations Density 0.000%

    No Known Activations