© 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. 2944
    Prev
    Next
    INDEX
    Explanations

    df assignment or operation

    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
    er
    -0.11
    pu
    -0.08
    ãģĦãģĪ
    -0.08
    schutz
    -0.08
    aler
    -0.08
    eren
    -0.07
    ality
    -0.07
    pard
    -0.07
    iy
    -0.07
    Ìģ
    -0.07
    POSITIVE LOGITS
    Ùĩ
    0.08
    °
    0.08
    icult
    0.08
    irtual
    0.08
    ¨
    0.07
    à¸Ľà¸£à¸°à¸Īำ
    0.07
    ventory
    0.07
    尼奥
    0.07
    erschaft
    0.07
    IRONMENT
    0.07
    Activations Density 0.004%

    No Known Activations