© 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. 49390
    Prev
    Next
    INDEX
    Explanations

    triggered Neymar

    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
    awi
    -0.08
    çĩ
    -0.07
    ic
    -0.07
    纬
    -0.06
    itzerland
    -0.06
     Offer
    -0.06
    èµĦæĸĻ
    -0.06
     اÙĦÙħØ·
    -0.06
    วล
    -0.06
    (IO
    -0.06
    POSITIVE LOGITS
    ustin
    0.09
    è¡ħ
    0.08
     Crushers
    0.08
    å´©
    0.07
    /change
    0.07
    Forge
    0.07
    æĶ¹äºĨ
    0.07
    缸åħ³éĹ®çŃĶ
    0.07
    -toggler
    0.07
    ä»·æł¼èµ°åĬ¿
    0.07
    Activations Density 0.343%

    No Known Activations