© 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. 39384
    Prev
    Next
    INDEX
    Explanations

    parenthood and motherhood

    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
    aneous
    -0.09
    使çĶ¨æĸ¹æ³ķ
    -0.07
    ç¨ĭ度ä¸Ĭ
    -0.07
    æĢ§éĹ®é¢ĺ
    -0.07
    ahas
    -0.07
     salvo
    -0.07
    æļĹæ²ī
    -0.07
    çļĦ使çĶ¨æĸ¹æ³ķ
    -0.07
    edReader
    -0.06
    edm
    -0.06
    POSITIVE LOGITS
    hood
    0.11
    thood
    0.10
    è¿Ļ个è§Ĵèī²
    0.09
     roles
    0.09
    è§Ĵèī²çļĦ
    0.08
    erschap
    0.08
    èµĦæł¼
    0.08
    manship
    0.08
     duties
    0.08
     experience
    0.08
    Activations Density 0.185%

    No Known Activations