© 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. 46922
    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
    wers
    -0.08
    ÙĨÙĬ
    -0.07
    ucci
    -0.07
    å¤įèĭı
    -0.07
    å¾ħ
    -0.06
    æİ¥å¾ħ
    -0.06
    utine
    -0.06
    ieu
    -0.06
    гÑĢ
    -0.06
    åħ¨åĽ½
    -0.06
    POSITIVE LOGITS
    andum
    0.07
    驾
    0.07
    ÙIJب
    0.07
    elen
    0.07
    eh
    0.07
    åŁºæľ¬è¦ģæ±Ĥ
    0.07
    骨åŃIJéĩĮ
    0.06
    IDL
    0.06
    çIJ³å¨ľ
    0.06
    lena
    0.06
    Activations Density 0.000%

    No Known Activations