© 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. 29147
    Prev
    Next
    INDEX
    Explanations

    Imagine, 's, was, remember

    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
    秫
    -0.08
    اجر
    -0.08
    estination
    -0.08
    eno
    -0.08
    <<<<<<<
    -0.07
    ãĥĭãĥ³ãĤ°
    -0.07
    criptors
    -0.07
    icontrol
    -0.07
    prite
    -0.07
    //*[@
    -0.07
    POSITIVE LOGITS
    ä¸Ģä¼ļ
    0.07
    é»į
    0.07
     Amor
    0.06
    wal
    0.06
     Aria
    0.06
    æIJŀ
    0.06
    æĬĬéĤ£
    0.06
    над
    0.06
    å®ĺ宣
    0.06
    zer
    0.05
    Activations Density 0.094%

    No Known Activations