© 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. 16957
    Prev
    Next
    INDEX
    Explanations

    prepared by, produced by

    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
    éĶIJæĦı
    -0.08
    éĶIJæĦıè¿Ľåıĸ
    -0.07
    ler
    -0.07
    è¡¥
    -0.07
     bitterly
    -0.07
    è£ľ
    -0.07
    cul
    -0.07
    ä¹ĭä¸ĭçļĦ
    -0.07
    ult
    -0.07
    Invoke
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩå°Ĩ
    0.18
     пÑĥÑĤем
    0.17
    éĢļè¿ĩåľ¨
    0.16
    à¹Ĥà¸Ķยà¸ģาร
    0.15
     à¹Ĥà¸Ķยà¸ģาร
    0.14
     indem
    0.14
     polega
    0.14
    å°±æĺ¯æĬĬ
    0.13
     consiste
    0.13
     à¸Ķà¹īวยà¸ģาร
    0.12
    Activations Density 0.722%

    No Known Activations