© 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. 48688
    Prev
    Next
    INDEX
    Explanations

    insurance related terms

    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
    tring
    -0.08
    полни
    -0.08
    inqu
    -0.07
    stående
    -0.07
    ted
    -0.07
    ropolis
    -0.07
     اÙĦدراسÙĬ
    -0.07
    rim
    -0.07
    /or
    -0.07
    trs
    -0.07
    POSITIVE LOGITS
    baugh
    0.10
    paralleled
    0.08
    èµ·è§ģ
    0.08
    olvency
    0.08
    seau
    0.08
    åijĺçļĦ
    0.08
    çIJĨèµĶ
    0.08
    è¦ĨçĽĸéĿ¢
    0.08
    ingly
    0.07
    ervation
    0.07
    Activations Density 0.040%

    No Known Activations