© 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. 63634
    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
    isiv
    -0.08
    ikum
    -0.08
    _Utils
    -0.07
    estring
    -0.07
    çļĦæ²Ļ
    -0.07
    ä»¥ä¹łè¿ijå¹³
    -0.07
    人åı£çļĦ
    -0.07
     ÑĢазнов
    -0.07
    ahi
    -0.07
     Wich
    -0.07
    POSITIVE LOGITS
    urs
    0.07
    ores
    0.07
    urse
    0.06
    acce
    0.06
    åīįæľī
    0.06
     ÑģбоÑĢ
    0.06
    ities
    0.06
    稽
    0.06
    ences
    0.06
     bolt
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.