© 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. 47712
    Prev
    Next
    INDEX
    Explanations

    motherhood, fatherhood, parents

    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
    ´
    -0.08
    zó
    -0.08
    ¯
    -0.07
    umber
    -0.07
    emente
    -0.07
    noch
    -0.07
    çĶ·å¥³
    -0.06
    tritt
    -0.06
    tober
    -0.06
    人士
    -0.06
    POSITIVE LOGITS
    hood
    0.12
    esco
    0.11
    less
    0.10
    å¨ĺå¨ĺ
    0.10
    -da
    0.10
    lessness
    0.09
    -child
    0.09
     ÑģемейÑģÑĤва
    0.09
    大人çļĦ
    0.09
    Ö¼
    0.08
    Activations Density 0.059%

    No Known Activations