© 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. 29342
    Prev
    Next
    INDEX
    Explanations

    version control identifiers

    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
    orsch
    -0.09
    ance
    -0.09
    æĪĸå¤ļ个
    -0.08
    ACLE
    -0.08
    Åijl
    -0.08
    ¯
    -0.08
    anches
    -0.08
    asures
    -0.08
    ضا
    -0.08
    รà¹Īาà¸ĩ
    -0.08
    POSITIVE LOGITS
    íĴĪ
    0.08
    ubern
    0.07
    ़
    0.07
    mente
    0.07
    zelfde
    0.07
    ลฯ
    0.07
    ues
    0.07
    Ñĥди
    0.07
    fully
    0.07
    ever
    0.07
    Activations Density 0.143%

    No Known Activations