© 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. 33783
    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
     br
    -0.06
    uari
    -0.06
    istant
    -0.06
     Minor
    -0.06
    zl
    -0.06
    OLID
    -0.06
     needing
    -0.06
    ì¼Ģ
    -0.06
     cashier
    -0.06
    alde
    -0.06
    POSITIVE LOGITS
    好åķĬ
    0.08
    tober
    0.08
     Charme
    0.08
     gee
    0.08
    මà·Ĭ
    0.07
    ccio
    0.07
    iry
    0.07
    inder
    0.07
    èĥ½å¤Łæ»¡è¶³
    0.07
    lify
    0.07
    Activations Density 0.000%

    No Known Activations