© 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. 29979
    Prev
    Next
    INDEX
    Explanations

    triangle shapes

    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
    夫åIJĽ
    -0.07
    åIJĽåŃIJ
    -0.06
     Breit
    -0.06
    kr
    -0.06
     halt
    -0.06
    é
    -0.06
    ä¸ĩåĪĨ
    -0.06
    ä¸Ī夫
    -0.06
     raised
    -0.06
    pher
    -0.06
    POSITIVE LOGITS
    èĥĮéĿł
    0.09
    ismatic
    0.08
    ãĥ³ãĥĪ
    0.08
     pouc
    0.08
    尼奥
    0.08
    ยà¹Īà¸Ńย
    0.08
    ิà¹Īม
    0.08
    umpa
    0.08
     aang
    0.08
     adjoining
    0.08
    Activations Density 0.006%

    No Known Activations