© 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. 43634
    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
    dc
    -0.06
    æĹłèģĬ
    -0.06
    rc
    -0.06
     dc
    -0.06
     Orth
    -0.06
     ...
    -0.05
     tranquill
    -0.05
     Silva
    -0.05
     outstanding
    -0.05
    -0.05
    POSITIVE LOGITS
    åĽ½ä¹ĭ
    0.09
    aign
    0.08
    éĢģæĪij
    0.08
    wizard
    0.08
    ä½łèº«è¾¹
    0.08
    helpers
    0.08
    zach
    0.08
    äºĨä¸Ģ件
    0.08
    -about
    0.08
    çĪ±æ°ij
    0.08
    Activations Density 0.000%

    No Known Activations