© 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. 29817
    Prev
    Next
    INDEX
    Explanations

    three or four

    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
    ency
    -0.08
    ستÙĩ
    -0.08
    ilus
    -0.07
    iau
    -0.07
    ereum
    -0.07
    ervis
    -0.07
    oland
    -0.07
    ertas
    -0.07
    ghan
    -0.07
    缺
    -0.07
    POSITIVE LOGITS
    rix
    0.07
     à¹Ħà¸Ķà¹īà¹ģà¸ģà¹Ī
    0.06
     extensive
    0.06
     available
    0.06
    ivered
    0.06
    *:
    0.06
    Wrong
    0.06
    utton
    0.06
     ant
    0.06
     Choices
    0.06
    Activations Density 0.001%

    No Known Activations