© 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. 8547
    Prev
    Next
    INDEX
    Explanations

    supported living services

    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
    çĤ«èĢĢ
    -0.07
    çĤ«
    -0.07
     resurrect
    -0.06
    æĬĸ
    -0.06
    -0.06
    éĺ²ä¼ª
    -0.06
     souvenirs
    -0.06
    åıįèħIJ
    -0.06
    éĽ
    -0.06
     unle
    -0.06
    POSITIVE LOGITS
     providers
    0.11
     caregiver
    0.11
    家访
    0.11
    -provider
    0.10
     services
    0.10
    å®īç½®
    0.10
    æĶ¶å®¹
    0.10
     provider
    0.10
     caregivers
    0.10
     referrals
    0.10
    Activations Density 0.393%

    No Known Activations