© 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. 22582
    Prev
    Next
    INDEX
    Explanations

    adiponectin, peroxisome proliferator-activated receptor gamma2

    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
    izas
    -0.07
    åħ¬å®³
    -0.07
    åIJīå®ī
    -0.07
    å¾·åĪ©
    -0.07
    è¾¹éĻħ
    -0.06
    尽头
    -0.06
    SYM
    -0.06
    ç±³äºļ
    -0.06
    ymb
    -0.06
    away
    -0.06
    POSITIVE LOGITS
    ICLES
    0.08
    çĪ±å²Ĺ
    0.07
     indicative
    0.07
     Commit
    0.07
    åĴĮ马
    0.07
    AsString
    0.07
     markers
    0.07
    æķıæĦŁçļĦ
    0.07
    åĽĽé¡¹
    0.07
     marker
    0.07
    Activations Density 0.979%

    No Known Activations