© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15018
    Prev
    Next
    INDEX
    Explanations

    times, dollar amounts, percent, or specific units

    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
    åĨħå¤ĸ
    -0.07
    çıį
    -0.07
    è½
    -0.07
    æ°¸
    -0.07
     Barca
    -0.07
    ä¸įèĩ³äºİ
    -0.07
    ï¼ļ"
    -0.06
    ))),
    -0.06
    .panel
    -0.06
     promis
    -0.06
    POSITIVE LOGITS
    âĢij
    0.10
    ).-
    0.09
    å°ıç¼ĸ为大家
    0.08
    ä¹Łç§°ä¸º
    0.07
    åıĬ以ä¸ĬçļĦ
    0.07
     поÑıÑģни
    0.07
    <\/
    0.07
    åľ°çĵľ
    0.07
    åįĩç´ļ
    0.07
    levision
    0.07
    Activations Density 0.001%

    No Known Activations