© 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. 10831
    Prev
    Next
    INDEX
    Explanations

    code syntax: closing braces

    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
    asiun
    -0.07
    setw
    -0.07
     Gri
    -0.07
    arani
    -0.07
    andon
    -0.07
     nets
    -0.07
    setUp
    -0.07
    Assignable
    -0.07
    rze
    -0.07
    arangan
    -0.07
    POSITIVE LOGITS
    èį·
    0.08
    饼
    0.07
    åģĩ
    0.07
    åijµ
    0.07
    ENE
    0.07
    εί
    0.07
    亦
    0.06
    ww
    0.06
    оÑı
    0.06
    bic
    0.06
    Activations Density 0.211%

    No Known Activations