© 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. 13959
    Prev
    Next
    INDEX
    Explanations

    methods and functions

    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
    /vendors
    -0.07
    .objects
    -0.07
    hop
    -0.07
     costituit
    -0.07
    .gov
    -0.07
    .scheme
    -0.07
    å¹´æĪIJç«ĭ
    -0.07
    -txt
    -0.07
     swept
    -0.07
    uzz
    -0.07
    POSITIVE LOGITS
     functions
    0.12
     callable
    0.11
    functions
    0.10
    åĩ½æķ°
    0.10
     Functions
    0.10
     fonctions
    0.10
     implementations
    0.10
     function
    0.10
    åĩ½æķ°çļĦ
    0.10
     ÑĦÑĥнкÑĨии
    0.09
    Activations Density 0.439%

    No Known Activations