© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49940
    Prev
    Next
    INDEX
    Explanations

    numbers as list items or references

    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
    oges
    -0.08
    aji
    -0.08
    zens
    -0.07
    æĶ¿å±Ģ
    -0.07
    -goal
    -0.07
    åĽĽåij¨
    -0.07
    attel
    -0.07
    redo
    -0.07
    /><
    -0.07
    æľĽ
    -0.07
    POSITIVE LOGITS
    LastError
    0.08
    çij
    0.08
    çijĻ
    0.08
    otka
    0.07
     ,[
    0.07
    aler
    0.07
    ISTER
    0.07
    thetic
    0.07
    istring
    0.07
    idak
    0.07
    Activations Density 0.029%

    No Known Activations