© 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. 38952
    Prev
    Next
    INDEX
    Explanations

    React import

    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
    vet
    -0.07
    nitz
    -0.07
    wis
    -0.06
    ä»Ģä¹Īä¸ľè¥¿
    -0.06
    æĮ
    -0.06
     deja
    -0.06
    Ľ
    -0.06
    çľģä¼ļ
    -0.06
     eng
    -0.06
    веÑĤа
    -0.06
    POSITIVE LOGITS
    ãĢģ
    0.08
    ulong
    0.08
    matcher
    0.08
    æ¿
    0.07
    RIES
    0.06
    ä»ĺ
    0.06
    æ½ĩ
    0.06
     ακÏĮ
    0.06
    æį·
    0.06
    æ¦Ī
    0.06
    Activations Density 0.183%

    No Known Activations