© 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. 64494
    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
    åŁł
    -0.07
    ecam
    -0.06
    ç©Ĺ
    -0.06
    蹦
    -0.06
    å¨ģåĬĽ
    -0.06
    gende
    -0.06
    缴æİ¥æĪĸ
    -0.06
    -random
    -0.06
    meld
    -0.06
    axter
    -0.06
    POSITIVE LOGITS
    æĥ³åĪ°è¿ĻéĩĮ
    0.08
    idor
    0.07
    æĺ¨å¤ľ
    0.07
    Ó©Ó©
    0.07
    åįıè°ĥåıijå±ķ
    0.07
    lad
    0.06
    .createElement
    0.06
    trup
    0.06
    à¸Ķิ
    0.06
    梯éĺŁ
    0.06
    Activations Density 0.000%

    No Known Activations