© 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. 47462
    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
    æĸĩçIJĨ
    -0.08
    ipan
    -0.07
    ynchronously
    -0.07
    ensi
    -0.07
    ãĢģ“
    -0.06
     Klos
    -0.06
    ัà¸Ļà¸Ĺ
    -0.06
    æĻ°
    -0.06
    èģĮä¸ļåѦéĻ¢
    -0.06
    elman
    -0.06
    POSITIVE LOGITS
    æľīåħ³è¦ģæ±Ĥ
    0.08
    è§Ħ模
    0.07
    defaults
    0.07
    chg
    0.07
     TNH
    0.07
     tre
    0.07
    è´Ŀåħĭ
    0.07
    thus
    0.07
    pty
    0.07
    untr
    0.07
    Activations Density 0.000%

    No Known Activations