© 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. 61253
    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
    é¢Ħ
    -0.08
    .pre
    -0.07
    ä¸įå¿ħè¦ģ
    -0.06
     reap
    -0.06
    为åħĪ
    -0.06
    cf
    -0.06
    apid
    -0.06
    ATIV
    -0.06
    acci
    -0.06
     padd
    -0.06
    POSITIVE LOGITS
    çī¹æĸ¯
    0.08
    baut
    0.07
    Tower
    0.07
    arz
    0.07
    orget
    0.07
    ç¼Ī
    0.07
    irror
    0.07
     Soleil
    0.07
    ezo
    0.07
    ÑģÑĤÑĮе
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.