© 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. 61912
    Prev
    Next
    INDEX
    Explanations

    linked list nodes

    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
    éļĶçĿĢ
    -0.08
    äºĭä¸Ń
    -0.07
     miejsc
    -0.07
    æĤī
    -0.07
    xAA
    -0.06
     terc
    -0.06
    oul
    -0.06
     dab
    -0.06
    ikka
    -0.06
    æ§Ľ
    -0.06
    POSITIVE LOGITS
    éĵ¾
    0.17
     chain
    0.16
    chain
    0.15
    éıĪ
    0.14
     chains
    0.14
    Chain
    0.13
    -chain
    0.13
    éĵ¾è¡¨
    0.13
     Chain
    0.13
     chained
    0.12
    Activations Density 0.167%

    No Known Activations