© 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. 46705
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
    strup
    -0.08
    çļĦ天çĦ¶
    -0.08
     Agility
    -0.07
    rie
    -0.07
    çķĻ
    -0.07
    _scheme
    -0.07
    æķħ人
    -0.07
    -application
    -0.07
    лона
    -0.07
    IgnoreCase
    -0.07
    POSITIVE LOGITS
     âĢº
    0.07
    ervo
    0.07
    illah
    0.06
    ajes
    0.06
    çī©è¯Ń
    0.06
    æĬľãģį
    0.06
    âl
    0.06
     vols
    0.06
    çu
    0.06
    Åĵur
    0.06
    Activations Density 0.092%

    No Known Activations