© 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. 21036
    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
    .enc
    -0.07
    antai
    -0.07
    èĻı
    -0.07
    antz
    -0.07
    ัà¸ĩ
    -0.07
    èĦijçŃĭ
    -0.06
    obat
    -0.06
    å¸ĸåŃIJ
    -0.06
    åħ¨èĥľ
    -0.06
    èĦijåŃIJ
    -0.06
    POSITIVE LOGITS
    chino
    0.07
    IfExists
    0.07
     palav
    0.07
    ottie
    0.07
    andro
    0.07
    °
    0.07
    Injector
    0.07
     einsetzen
    0.07
    çĪ
    0.07
     tempt
    0.07
    Activations Density 0.000%

    No Known Activations