© 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. 50256
    Prev
    Next
    INDEX
    Explanations

    sample size

    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
    èµĸ
    -0.09
    emis
    -0.09
    astre
    -0.08
    istos
    -0.08
    ×Ļר×ķת
    -0.08
    weiler
    -0.08
    é¡ŀ
    -0.08
    enger
    -0.07
     Recu
    -0.07
    _gettime
    -0.07
    POSITIVE LOGITS
    æł·æľ¬
    0.09
     statistics
    0.08
    _size
    0.08
    ä¸ŃçļĦ
    0.08
    ä¸Ģç»Ħ
    0.08
     sizes
    0.08
    ä¸Ńæľī
    0.08
     samples
    0.08
    -wide
    0.08
     size
    0.08
    Activations Density 0.004%

    No Known Activations