© 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. 38766
    Prev
    Next
    INDEX
    Explanations

    technical and programming terms

    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
    aliz
    -0.09
    .CR
    -0.09
    ].[
    -0.08
    धि
    -0.08
     ("-
    -0.08
     (![
    -0.08
    ].'
    -0.08
    _IMPLEMENT
    -0.08
    àºŃàºĩ
    -0.08
    èı²èı²
    -0.08
    POSITIVE LOGITS
     _____
    0.11
    ____
    0.11
    \"
    0.11
     ____
    0.11
     ______
    0.10
    _____
    0.09
     âĢ¦
    0.09
     ________
    0.09
     ___
    0.09
    ___
    0.09
    Activations Density 0.041%

    No Known Activations