© 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. 4241
    Prev
    Next
    INDEX
    Explanations

    basic/symmetric/reverse/independent

    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
     Fiorent
    -0.09
     Mattis
    -0.08
    ayers
    -0.07
    enn
    -0.07
    zer
    -0.07
    ennen
    -0.07
    å°ıçļĦæŶåĢĻ
    -0.07
     netr
    -0.07
    rons
    -0.07
    åħ¬åı¸åıijå±ķ
    -0.07
    POSITIVE LOGITS
    ìŀIJìĿ¸
    0.08
     den
    0.07
    æŁł
    0.07
    chl
    0.07
     bernama
    0.07
    orthand
    0.07
    åIJĮåIJį
    0.06
    ìĭľíĶ¼
    0.06
    çĿ
    0.06
    åĪ°ä½į
    0.06
    Activations Density 0.116%

    No Known Activations