© 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. 33074
    Prev
    Next
    INDEX
    Explanations

    intermediate states or phases

    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
     rán
    -0.07
    idou
    -0.07
    roe
    -0.07
    yg
    -0.07
    ingin
    -0.07
    EFR
    -0.07
    letcher
    -0.07
     Blan
    -0.06
    éĽĨåĽ¢åľ¨
    -0.06
    жениÑı
    -0.06
    POSITIVE LOGITS
     intermediate
    0.17
     intermediary
    0.17
     intermedi
    0.15
     Intermediate
    0.14
    ä¸ŃéĹ´
    0.14
    Intermediate
    0.13
    ä¸Ńä»ĭ
    0.13
     пÑĢомежÑĥ
    0.12
     poÅĽred
    0.12
    ä¸Ń转
    0.12
    Activations Density 0.084%

    No Known Activations