© 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. 42875
    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
     writable
    -0.08
    åIJįåī¯
    -0.07
    lie
    -0.07
    enner
    -0.07
    ymes
    -0.07
     true
    -0.07
    ommer
    -0.07
    esses
    -0.07
    为äºĨ满足
    -0.07
    rote
    -0.06
    POSITIVE LOGITS
    çĦķ
    0.08
    urg
    0.07
    è³ĩ
    0.07
     Bev
    0.07
    èĬĴ
    0.07
    èµĦ
    0.07
    urgo
    0.07
     Neub
    0.07
     Ú©ÙĪتاÙĩ
    0.07
    resources
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.