© 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. 12902
    Prev
    Next
    INDEX
    Explanations

    html table cell (`<td>`)

    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
    jö
    -0.06
    æµ·å¤ĸ
    -0.06
     folly
    -0.06
    루
    -0.06
     system
    -0.06
    åĪ©æ°ij
    -0.05
     flick
    -0.05
     ext
    -0.05
    herme
    -0.05
    ång
    -0.05
    POSITIVE LOGITS
     colspan
    0.11
     cell
    0.10
    zellen
    0.10
    (Cell
    0.10
    Cell
    0.09
     CELL
    0.09
    ç»ĨèĥŀçļĦ
    0.09
    CELL
    0.09
    <td
    0.09
     Cells
    0.09
    Activations Density 0.074%

    No Known Activations