© 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. 30270
    Prev
    Next
    INDEX
    Explanations

    electromagnetic, graphical, frequency, linear, red

    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
    奶çĪ¸
    -0.08
    мли
    -0.07
    è¿ĶåĽŀåĪĹ表
    -0.07
    ocio
    -0.07
    ReactDOM
    -0.07
    bsd
    -0.07
    PAGE
    -0.07
    âl
    -0.06
    ãm
    -0.06
    (mi
    -0.06
    POSITIVE LOGITS
    èĢĮå¾ĹåIJį
    0.11
    oroz
    0.09
     appunto
    0.09
     itself
    0.08
    athan
    0.07
    åıĬ缸åħ³
    0.07
     itse
    0.06
     themselves
    0.06
    æķħåIJį
    0.06
    ehlen
    0.06
    Activations Density 0.579%

    No Known Activations