© 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. 18015
    Prev
    Next
    INDEX
    Explanations

    commands or actions

    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
     beaten
    -0.06
    on
    -0.06
    åĪ°
    -0.06
    lah
    -0.06
    ·
    -0.06
    ħ
    -0.06
    âij
    -0.06
    ur
    -0.06
    ı
    -0.06
    la
    -0.06
    POSITIVE LOGITS
    جرد
    0.09
    atteristiche
    0.09
    é½IJé½IJ
    0.08
     alasti
    0.08
    areth
    0.08
    á´Ħ
    0.08
    ulette
    0.08
    gether
    0.08
    errupted
    0.08
     AssertionError
    0.08
    Activations Density 0.009%

    No Known Activations