© 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. 19132
    Prev
    Next
    INDEX
    Explanations

    html paragraphs

    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
    OwnProperty
    -0.08
    赶紧æĿ¥
    -0.07
    ↵↵
    -0.06
    éľĢçĶ¨
    -0.06
    æīįçŁ¥éģĵ
    -0.06
    ettino
    -0.06
    .Of
    -0.06
    çĤ¹åĩ»æŁ¥çľĭ
    -0.06
    ught
    -0.06
    å¿ħçľĭ
    -0.06
    POSITIVE LOGITS
     furthermore
    0.08
    VG
    0.07
    æѤå¤ĸ
    0.07
     Sipil
    0.07
    以ä¸Ĭå°±æĺ¯
    0.07
    为äºĨèĥ½
    0.07
    以ä¸Ĭ
    0.07
     Mahm
    0.07
    æĭīæĸ¯
    0.07
    orst
    0.07
    Activations Density 0.040%

    No Known Activations