© 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. 57574
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    çĽ²
    -0.08
    neas
    -0.08
    为主导
    -0.07
    ãģļãģ¤
    -0.07
    ä¹Łæľīå¾Īå¤ļ
    -0.07
    åľ°å¯¹
    -0.07
    ehm
    -0.07
    ĶĦ
    -0.07
    ÑĢово
    -0.07
    .ERR
    -0.07
    POSITIVE LOGITS
    çļĦçŃĶæ¡Ī
    0.15
    çŃĶæ¡Īæĺ¯
    0.14
    çŃĶæ¡Ī
    0.14
     answered
    0.13
     answer
    0.13
     Answer
    0.12
    çļĦåĽŀçŃĶ
    0.12
    Answer
    0.12
    çŃĶãģĪ
    0.12
    åĽŀçŃĶ
    0.12
    Activations Density 0.183%

    No Known Activations