© 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. 26395
    Prev
    Next
    INDEX
    Explanations

    someone or somebody

    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
    注æĦıä¼ijæģ¯
    -0.08
     rowNum
    -0.08
    istere
    -0.08
    åħ¨éĥ¨éĥ½
    -0.08
    INY
    -0.08
    åıªçĶ¨
    -0.08
    Spoiler
    -0.08
    .utc
    -0.08
    åıªçŁ¥éģĵ
    -0.08
    eto
    -0.08
    POSITIVE LOGITS
     alguém
    0.10
     someone
    0.08
    åĩºèĩª
    0.08
     jemand
    0.07
     alguien
    0.07
    someone
    0.07
    大æ¦Ĥæĺ¯
    0.07
    ä¸Ģ个人
    0.06
     somebody
    0.06
    çĶ¨äºİ
    0.06
    Activations Density 0.005%

    No Known Activations