© 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. 16272
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    åĭĴç´¢
    -0.07
    å°ĸ
    -0.07
    åı£
    -0.06
     sneak
    -0.06
     gam
    -0.06
    /train
    -0.06
    彩礼
    -0.06
    ffy
    -0.06
    dsn
    -0.06
    åĬłæ²¹
    -0.06
    POSITIVE LOGITS
    éļIJå±ħ
    0.11
    å±ĪåİŁ
    0.10
    èĭıè½¼
    0.10
    æ¸Ĭæĺİ
    0.09
    æĹ·
    0.08
    inson
    0.08
    çĥ¦
    0.08
    åѤå¯Ĥ
    0.08
    请ä¸İ
    0.08
    è±ģè¾¾
    0.08
    Activations Density 0.005%

    No Known Activations