© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34018
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     поне
    -0.07
    inski
    -0.07
    该èĤ¡
    -0.07
    emers
    -0.07
    ocz
    -0.07
    æķĻäºİ
    -0.07
    大ä¸Ń
    -0.07
    yny
    -0.07
    .overflow
    -0.07
    stig
    -0.07
    POSITIVE LOGITS
    igus
    0.08
    夹
    0.07
    ذا
    0.06
    央
    0.06
     central
    0.06
    Mah
    0.06
    .
    0.06
    夾
    0.06
    éĢĶ
    0.06
    tu
    0.06
    Activations Density 0.171%

    No Known Activations