© 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. 63672
    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
    æµı
    -0.08
    çĢı
    -0.08
    ä¸ĢäºĮ
    -0.08
     ÐļÑĢаÑģи
    -0.08
    IRST
    -0.07
     häuf
    -0.07
    onio
    -0.07
    geg
    -0.07
    åľ¨åı°
    -0.07
    sez
    -0.07
    POSITIVE LOGITS
    cid
    0.07
    enable
    0.06
    kaw
    0.06
     ind
    0.06
    uro
    0.06
    _argument
    0.06
    éģĹ
    0.06
    uron
    0.06
    uri
    0.06
     intent
    0.06
    Activations Density 0.000%

    No Known Activations