© 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. 29269
    Prev
    Next
    INDEX
    Explanations

    java imports and utilities

    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
    voli
    -0.08
    ihal
    -0.08
    اد
    -0.08
    onus
    -0.08
    PrototypeOf
    -0.08
    äºĭæķħçļĦåıijçĶŁ
    -0.08
    TING
    -0.08
    гада
    -0.08
    anghai
    -0.07
    tings
    -0.07
    POSITIVE LOGITS
    .util
    0.08
    ìĪł
    0.07
     Tew
    0.07
    ç²¾
    0.07
     IP
    0.07
     util
    0.06
    åľı
    0.06
    ÙĬØ©
    0.06
    éĻħ
    0.06
     stream
    0.06
    Activations Density 0.048%

    No Known Activations