© 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. 11876
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming constructs

    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
    /../
    -0.08
    夥
    -0.07
    åľŁèĢ³
    -0.07
    æĿİå°ı
    -0.07
    arkin
    -0.07
    komst
    -0.07
    innie
    -0.07
    ','=','
    -0.07
    feit
    -0.07
    çĮ®ç»Ļ
    -0.07
    POSITIVE LOGITS
    çīĻ
    0.06
     eskort
    0.06
    <|fim_suffix|>
    0.06
     reve
    0.06
     pard
    0.06
    try
    0.06
     amongst
    0.06
    ä¸įæ±Ĥ
    0.06
     TRY
    0.06
    TRY
    0.06
    Activations Density 0.092%

    No Known Activations