© 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. 32602
    Prev
    Next
    INDEX
    Explanations

    examples (e.g

    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
    se
    -0.09
    ÑģÑı
    -0.08
    alisi
    -0.08
     Grosso
    -0.08
    ulte
    -0.08
    çī¹æѤ
    -0.07
    udos
    -0.07
    å¤ļãģĦ
    -0.07
    zburg
    -0.07
    åħĥèĢģ
    -0.07
    POSITIVE LOGITS
    .,
    0.11
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.10
    .:
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    bara
    0.07
    emente
    0.07
     ëĵ¤ìĸ´
    0.07
    åŃIJéĩĮ
    0.07
    irth
    0.07
    .:**
    0.07
    Activations Density 0.054%

    No Known Activations