© 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. 1603
    Prev
    Next
    INDEX
    Explanations

    heart emotions and states

    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
    ëĩ¨
    -0.09
    ensial
    -0.09
    lare
    -0.08
    踪
    -0.08
    åħ¢åħ¢ä¸ļä¸ļ
    -0.08
    ifar
    -0.08
    otope
    -0.08
    åĻ©æ¢¦
    -0.08
    à¥Īया
    -0.08
    éĬŃ
    -0.08
    POSITIVE LOGITS
    æ·±å¤Ħ
    0.15
    æ·±å¤ĦçļĦ
    0.14
    åĴĮè¡Į为
    0.09
    åĴĮè¡ĮåĬ¨
    0.09
    tie
    0.08
    åĴĮç²¾ç¥ŀ
    0.07
    å±ĤéĿ¢çļĦ
    0.07
    å±ĤéĿ¢
    0.07
    ache
    0.07
    à¸Ńà¸ģ
    0.07
    Activations Density 0.057%

    No Known Activations