© 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. 11592
    Prev
    Next
    INDEX
    Explanations

    literature 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
    .visual
    -0.08
    osate
    -0.08
    æĬĺ
    -0.08
    ämm
    -0.08
    -original
    -0.07
    åŀĤ
    -0.07
    öger
    -0.07
    ÑĢоÑģло
    -0.07
    volo
    -0.07
    idar
    -0.07
    POSITIVE LOGITS
    çİĭä¹ĭ
    0.07
    less
    0.06
    sey
    0.06
    jo
    0.06
     fund
    0.06
    اÙĨس
    0.06
     rest
    0.06
    Tim
    0.06
     fluid
    0.06
    cap
    0.06
    Activations Density 0.003%

    No Known Activations