© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17283
    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
    å·¨åŀĭ
    -0.07
    done
    -0.07
    erst
    -0.06
    illard
    -0.06
    Undo
    -0.06
    plit
    -0.06
    illas
    -0.06
    çİ°
    -0.06
    hão
    -0.06
    CHA
    -0.06
    POSITIVE LOGITS
    åŁŁ
    0.08
    à¹īาà¸Ļ
    0.08
    äºĮè¦ģ
    0.07
    àµĩà´·
    0.07
    евна
    0.07
    ×Ļף
    0.07
    оÑĢий
    0.07
    ear
    0.07
    .hidden
    0.07
    åĽ½å®¶æĶ¿çŃĸ
    0.07
    Activations Density 0.000%

    No Known Activations