© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48292
    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
    ooter
    -0.09
    apis
    -0.08
    -API
    -0.08
    åħ¶ä»ĸæĸ¹å¼ı
    -0.08
    apkan
    -0.08
    undu
    -0.08
    ä¸ĢæľĽ
    -0.08
    溶äºİ
    -0.08
    conomy
    -0.07
    udia
    -0.07
    POSITIVE LOGITS
    amburg
    0.07
    igest
    0.06
    andest
    0.06
    aire
    0.06
     Hogan
    0.06
     Hutchinson
    0.06
    ç¹°
    0.06
    éķ¿è¶³
    0.06
     desg
    0.06
    P
    0.06
    Activations Density 0.000%

    No Known Activations