© 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. 40823
    Prev
    Next
    INDEX
    Explanations

    Michigan App. reports

    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
     Armenian
    -0.11
     NSW
    -0.10
     Azer
    -0.09
    debian
    -0.09
     Armen
    -0.09
    åľ©
    -0.09
     ÐĵÑĢÑĥзии
    -0.09
     Tennessee
    -0.09
     Armenia
    -0.09
     Basel
    -0.09
    POSITIVE LOGITS
    åĨĢ
    0.13
    天津
    0.12
    京津åĨĢ
    0.12
    滦
    0.12
    京津
    0.12
    æ²³åĮĹçľģ
    0.12
    渤海
    0.12
    çŁ³å®¶åºĦ
    0.12
    æĺ¯åĮĹ京
    0.12
    æ²³åĮĹ
    0.12
    Activations Density 1.368%

    No Known Activations