© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    prenatal alcohol and fetal development

    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
     hÆ°u
    -0.08
    èĢ
    -0.08
    éĢIJ级
    -0.08
    ä¸ļä½Ļ
    -0.07
    ллÑİ
    -0.07
    ierarchical
    -0.07
    agi
    -0.07
    hie
    -0.07
    MediaType
    -0.07
    æ¶Ī
    -0.07
    POSITIVE LOGITS
    èĥİ
    0.11
     prenatal
    0.10
     reproductive
    0.09
     unborn
    0.09
    宫åĨħ
    0.09
    èĥİåĦ¿
    0.09
     embryo
    0.09
    åŃķæľŁ
    0.09
    ä¼łéĢĴç»Ļ
    0.09
    åĩºçĶŁåIJİ
    0.08
    Activations Density 0.177%

    No Known Activations