© 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. 51476
    Prev
    Next
    INDEX
    Explanations

    separators and lines

    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
    ToOne
    -0.08
    figcaption
    -0.08
    å±ķå¼Ģåħ¨æĸĩ
    -0.08
    身ä¸Ĭä¸ĭ
    -0.08
    ekin
    -0.07
    è¿Ļä¸ľè¥¿
    -0.07
     "-",
    -0.07
    ussen
    -0.07
    æݨèįIJæľ¬ä¹¦
    -0.07
    profil
    -0.07
    POSITIVE LOGITS
    laki
    0.06
    lw
    0.06
    anner
    0.06
    æ«
    0.06
    udou
    0.06
     Barg
    0.06
    tika
    0.06
    abelle
    0.06
    ä»ĸçĶ¨
    0.06
    à¸ļาล
    0.06
    Activations Density 0.004%

    No Known Activations