© 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. 9760
    Prev
    Next
    INDEX
    Explanations

    placenta and placental health

    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
     miser
    -0.08
    åºIJ
    -0.07
    .opensource
    -0.07
    omie
    -0.07
     aposent
    -0.06
     restaur
    -0.06
    ãģ¤ãģij
    -0.06
     lids
    -0.06
    æįº
    -0.06
     Domen
    -0.06
    POSITIVE LOGITS
     abortion
    0.11
    åŃķ
    0.10
    èĥİ
    0.10
    æµģ产
    0.10
    èĥİçĽĺ
    0.10
    åĪĨ娩
    0.10
    å¦Ĭå¨ł
    0.10
     abortions
    0.10
    娩
    0.10
     pregnancy
    0.09
    Activations Density 0.099%

    No Known Activations