© 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. 30912
    Prev
    Next
    INDEX
    Explanations

    half

    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
    æĭĶ
    -0.09
    anden
    -0.08
    irman
    -0.08
    ãĤ¦ãĥ«
    -0.07
     borr
    -0.07
    ä¸įæĭĶ
    -0.07
    ÏĢο
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    ISTS
    -0.07
    bote
    -0.07
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.12
    äºĨä¸ĢåįĬ
    0.11
     half
    0.11
    half
    0.10
    -half
    0.10
     Half
    0.09
    åı¦ä¸ĢåįĬ
    0.09
    Half
    0.09
     halves
    0.09
    åįĬ
    0.08
    Activations Density 0.059%

    No Known Activations