© 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. 47358
    Prev
    Next
    INDEX
    Explanations

    functional equations with 'f'

    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
    _STAT
    -0.07
    ikum
    -0.07
    iÄį
    -0.07
    èŀįèµĦèŀįåĪ¸
    -0.07
    utow
    -0.07
    bjerg
    -0.07
    MITTED
    -0.07
     #__
    -0.07
    rian
    -0.07
    åħĭéļ¾
    -0.06
    POSITIVE LOGITS
    -delete
    0.08
    leet
    0.08
     uniform
    0.07
     consistently
    0.07
    çļĦä¸ĢåĪĩéĥ½
    0.07
     leve
    0.07
     leves
    0.07
    оек
    0.07
    Uniform
    0.07
    uniform
    0.07
    Activations Density 0.009%

    No Known Activations