© 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. 4002
    Prev
    Next
    INDEX
    Explanations

    positive abstract concepts

    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
    ç¡
    -0.09
    ç§ķ
    -0.07
    bish
    -0.07
    _named
    -0.07
    least
    -0.07
    æĭĻ
    -0.07
    æīĵè¿ĩ
    -0.07
    åĮĹè¾°
    -0.07
    èĩĬ
    -0.07
    izarre
    -0.07
    POSITIVE LOGITS
    åıªé¡¾
    0.10
     blindly
    0.10
    ä¸Ģåij³
    0.09
    è¿ĩåĪĨ
    0.09
    è¿Ļä¹Īå¤ļ
    0.09
    ä¸įèĥ½å®Įåħ¨
    0.09
    ä¹Łè¦ģ注æĦı
    0.08
    èĢĮæĹł
    0.08
    è¿ĺä¸įå¤Ł
    0.08
    太è¿ĩ
    0.08
    Activations Density 0.112%

    No Known Activations