© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10520
    Prev
    Next
    INDEX
    Explanations

    initialization code

    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
    oles
    -0.08
    å±ı
    -0.08
    aisu
    -0.07
    ola
    -0.07
    åģİ
    -0.07
     Myers
    -0.07
     bis
    -0.07
    ude
    -0.07
    桦
    -0.07
     bes
    -0.06
    POSITIVE LOGITS
    scratch
    0.09
    initialized
    0.09
     initialised
    0.09
    ä¸īæĹł
    0.08
     Initialized
    0.08
    æIJĶ
    0.08
    initialize
    0.08
    addock
    0.08
    cratch
    0.07
     initialValue
    0.07
    Activations Density 0.153%

    No Known Activations