© 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. 61705
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with parentheses

    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
    arno
    -0.07
    ardon
    -0.07
     noqa
    -0.06
    kehr
    -0.06
    hadap
    -0.06
    ÑĢекÑĤоÑĢ
    -0.06
    ,
    -0.06
    åħ¼ä»»
    -0.06
     Trent
    -0.06
    ç»°
    -0.05
    POSITIVE LOGITS
    ()(
    0.08
    hend
    0.08
    ÛĮب
    0.08
    yps
    0.08
    åѵ
    0.08
    ...(
    0.08
    upe
    0.07
    umpf
    0.07
    ikas
    0.07
     *@
    0.07
    Activations Density 0.029%

    No Known Activations