© 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. 38437
    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
    ä»Ģä¹Īåij¢
    -0.08
    å®ļäºİ
    -0.08
    apta
    -0.08
     //~
    -0.08
     ìĶ
    -0.08
    еÑĩе
    -0.08
    ace
    -0.08
    ìĬ¹
    -0.07
    वार
    -0.07
    计
    -0.07
    POSITIVE LOGITS
    ä¹Ł
    0.06
    demand
    0.06
     unders
    0.06
     demanding
    0.06
    alp
    0.06
    toy
    0.06
    avat
    0.06
    Demand
    0.06
    amples
    0.06
    emand
    0.06
    Activations Density 0.000%

    No Known Activations