© 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. 45022
    Prev
    Next
    INDEX
    Explanations

    dictionary keys

    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
    ysi
    -0.08
    éķ¿åº¦çļĦ
    -0.08
     length
    -0.08
     lengths
    -0.08
    .rawValue
    -0.08
    éķ¿åº¦
    -0.07
    è¿Ļæł¹
    -0.07
    çļĦéķ¿åº¦
    -0.07
    _length
    -0.07
    igas
    -0.07
    POSITIVE LOGITS
    dic
    0.09
     keys
    0.08
    dict
    0.08
    -keys
    0.08
     dict
    0.07
    keys
    0.07
     Dictionary
    0.07
     {'
    0.07
    ['
    0.07
     parameters
    0.07
    Activations Density 0.215%

    No Known Activations