© 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. 11104
    Prev
    Next
    INDEX
    Explanations

    string manipulation

    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
     pek
    -0.07
    trys
    -0.06
     Rakyat
    -0.06
    Transition
    -0.06
    ocard
    -0.06
    uhl
    -0.06
    umm
    -0.06
    ocio
    -0.06
    eth
    -0.06
     grades
    -0.06
    POSITIVE LOGITS
    åIJİçļĦ
    0.13
    åIJİè¿Ľè¡Į
    0.10
     puis
    0.09
    åIJİåĨį
    0.09
    åIJİç»ı
    0.09
     finally
    0.09
    åIJİçĶ¨
    0.08
    å¾ĮçļĦ
    0.08
    åIJİæľī
    0.08
    çĶŁæķĪåIJİ
    0.08
    Activations Density 0.094%

    No Known Activations