© 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. 2618
    Prev
    Next
    INDEX
    Explanations

    abstract emotions and struggles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     наÑģÑĤ
    -0.07
     offended
    -0.07
    åħµé©¬
    -0.07
     coordin
    -0.06
    æĹ©ä¸Ĭ
    -0.06
    çºĤ
    -0.06
     nomin
    -0.06
     coordinated
    -0.06
     Surprise
    -0.06
     coordinating
    -0.06
    POSITIVE LOGITS
    åĬŀçIJĨæµģç¨ĭ
    0.08
    fragment
    0.08
    æĮ£æīİ
    0.08
     Kafka
    0.07
    管å±Ģ
    0.07
     cla
    0.07
    çīĩä¸Ń
    0.07
    æ³¢çī¹
    0.07
     struggles
    0.07
     protagonist
    0.07
    Activations Density 0.092%

    No Known Activations