© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    akin or similar to

    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
     dint
    -0.07
    éĶŃ
    -0.07
    以赴
    -0.07
    è¡·å¿ĥ
    -0.06
    arded
    -0.06
     presumably
    -0.06
    orne
    -0.06
    urred
    -0.06
    رائ
    -0.06
    大æ³ķ
    -0.06
    POSITIVE LOGITS
     halnya
    0.13
    类似
    0.12
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.11
    æŀģäºĨ
    0.11
     similar
    0.10
    类似çļĦ
    0.10
     ähnliche
    0.09
    similar
    0.09
    é¡ŀä¼¼
    0.09
    Similar
    0.09
    Activations Density 0.085%

    No Known Activations