© 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. 50176
    Prev
    Next
    INDEX
    Explanations

    condensation, consumption, weight, steam, volume, potentials

    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
    assen
    -0.07
     subscribed
    -0.07
    chand
    -0.06
     wink
    -0.06
    çĨŁçŁ¥çļĦ
    -0.06
     administered
    -0.06
    æĺİçŁ¥
    -0.06
    umkan
    -0.06
    inja
    -0.06
     Admin
    -0.06
    POSITIVE LOGITS
    æݨå¼Ģ
    0.09
    åĩºæĿ¥åIJİ
    0.09
    èħ¾
    0.09
     GENERATED
    0.09
    veda
    0.09
    generated
    0.08
     generated
    0.08
     emerging
    0.08
     Generated
    0.08
    ael
    0.08
    Activations Density 0.119%

    No Known Activations