© 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. 22600
    Prev
    Next
    INDEX
    Explanations

    injury or damage

    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
    ault
    -0.07
    ismet
    -0.07
    _InitStruct
    -0.07
     Sweat
    -0.07
     Steele
    -0.07
    aranya
    -0.06
    æĥ³åIJĥ
    -0.06
     tráºŃt
    -0.06
    onos
    -0.06
    çIJIJ
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Ī大
    0.09
     Aw
    0.07
    aty
    0.07
    ,arr
    0.07
     inform
    0.06
     contexte
    0.06
    ugi
    0.06
    ToObject
    0.06
    éªĹ
    0.06
     involved
    0.06
    Activations Density 0.114%

    No Known Activations