© 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. 45053
    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
    urgeon
    -0.08
    æĺ¯ä»¶
    -0.08
    eree
    -0.07
    дел
    -0.07
    edException
    -0.07
    ulai
    -0.07
     Olah
    -0.07
    Disposition
    -0.07
    ession
    -0.07
    AMAN
    -0.07
    POSITIVE LOGITS
    /*@
    0.07
    enius
    0.07
    ague
    0.07
    chau
    0.07
    ave
    0.07
    xee
    0.06
    éĿĴé¾Ļ
    0.06
    亲åıĭ
    0.06
    azine
    0.06
     nors
    0.06
    Activations Density 0.000%

    No Known Activations