© 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. 9897
    Prev
    Next
    INDEX
    Explanations

    else followed by branch or false

    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
    ế
    -0.09
    -0.09
     latter
    -0.09
    λιÏĥ
    -0.08
    folge
    -0.08
    illin
    -0.08
    eces
    -0.08
    ners
    -0.08
    urtle
    -0.07
    edly
    -0.07
    POSITIVE LOGITS
    phine
    0.10
    Ùĩ
    0.09
    hoot
    0.08
    ãĢħãģ®
    0.08
    ington
    0.08
    Ñĥ
    0.08
    ftware
    0.08
    es
    0.08
    ãĢħ
    0.07
    vier
    0.07
    Activations Density 0.009%

    No Known Activations