© 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. 58690
    Prev
    Next
    INDEX
    Explanations

    telling or informing someone

    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
    çĶ±å¸Ĥ
    -0.08
    çĶ±ä¹Ļæĸ¹
    -0.08
    两个人çļĦ
    -0.08
    çļĦ人çī©
    -0.07
    å¾·éŁ³
    -0.07
    æĪijèĩªå·±çļĦ
    -0.07
    çĪ¸çĪ¸çļĦ
    -0.07
    çĶ·äººçļĦ
    -0.07
    ç»ıæµİä¸İ
    -0.07
    жели
    -0.07
    POSITIVE LOGITS
     us
    0.14
     anyone
    0.12
     you
    0.12
     him
    0.11
    ä¸ĸ人
    0.11
    ä»»ä½ķ人
    0.11
     anybody
    0.10
    人们
    0.10
     ваÑģ
    0.10
    人以
    0.09
    Activations Density 1.228%

    No Known Activations