© 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. 58063
    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
    oad
    -0.08
    หลวà¸ĩ
    -0.08
    èIJĿ
    -0.08
    èį¯æķĪ
    -0.07
    usercontent
    -0.07
    antly
    -0.07
    otron
    -0.07
    çĪ±ä¸įéĩĬ
    -0.07
    enda
    -0.07
    usul
    -0.07
    POSITIVE LOGITS
    _COD
    0.07
    åĭĭ
    0.06
    æĭ©ä¼ĺ
    0.06
     choice
    0.06
    ringer
    0.06
    science
    0.06
    hardt
    0.06
    _CALLBACK
    0.06
    åļ¼
    0.06
    ä¸Ģæĥ³åĪ°
    0.06
    Activations Density 0.000%

    No Known Activations