© 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. 50208
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and processes

    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
    raid
    -0.08
     bezo
    -0.07
    relations
    -0.06
    èį·è½½
    -0.06
     Shed
    -0.06
    izi
    -0.06
    å¹ħ
    -0.06
    è·
    -0.06
    主æĮģåı¬å¼Ģ
    -0.06
    imeo
    -0.06
    POSITIVE LOGITS
    -style
    0.08
     whereby
    0.08
    åį³çĶ¨
    0.07
    ê±°
    0.07
    è´±
    0.07
     redux
    0.07
     involving
    0.07
    è¿ĺåİŁ
    0.07
    çĶ¨çļĦæĺ¯
    0.07
    çĶ¨è¿ĩ
    0.07
    Activations Density 0.011%

    No Known Activations