© 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. 42956
    Prev
    Next
    INDEX
    Explanations

    definition of terms

    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
    为éĩį
    -0.10
    abu
    -0.09
    ãĤ¤ãĥĦ
    -0.09
    ụt
    -0.09
    äºļçī¹
    -0.09
    fällig
    -0.09
    eley
    -0.08
    åĪĺçķħ
    -0.08
    rave
    -0.08
    æĹłæŀģ
    -0.08
    POSITIVE LOGITS
    表述
    0.10
    è¿Ļåı¥è¯Ŀ
    0.09
    è¿Ļè¯Ŀ
    0.08
     phrase
    0.08
    主è¯Ń
    0.07
     "
    0.07
    说æ³ķ
    0.07
     lawful
    0.07
    è¨Ģ
    0.07
     saying
    0.07
    Activations Density 0.005%

    No Known Activations