© 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. 30505
    Prev
    Next
    INDEX
    Explanations

    conditional logic

    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
    acos
    -0.08
    ÑĪне
    -0.08
    atel
    -0.07
    egu
    -0.07
    atele
    -0.07
    "group
    -0.07
    åĽłäººèĢĮå¼Ĥ
    -0.07
    ä¹±çļĦ
    -0.07
    بÙĥØ©
    -0.07
    ujet
    -0.07
    POSITIVE LOGITS
    ior
    0.07
    åd
    0.07
    ä½łæ²¡
    0.06
    ãĤĪ
    0.06
    ä»Ģä¹Īéĥ½æ²¡
    0.06
    ør
    0.06
    omit
    0.06
     Cald
    0.06
    vin
    0.06
    dor
    0.06
    Activations Density 0.001%

    No Known Activations