© 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. 33566
    Prev
    Next
    INDEX
    Explanations

    unresponsive to treatment

    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
    å¼łæµ·
    -0.07
    AIL
    -0.07
    åĶı
    -0.06
     freig
    -0.06
    伪
    -0.06
    KH
    -0.06
    æĬ¢åħĪ
    -0.06
    AspNet
    -0.06
    èªī
    -0.06
     <->
    -0.06
    POSITIVE LOGITS
     persists
    0.11
     persist
    0.11
     stubborn
    0.10
     persisted
    0.10
     Persist
    0.10
     persistent
    0.10
    Persist
    0.10
    persistent
    0.10
     persistence
    0.09
    ä»įæľª
    0.09
    Activations Density 0.274%

    No Known Activations