© 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. 46069
    Prev
    Next
    INDEX
    Explanations

    grandparents and grandchildren

    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
    tures
    -0.08
    beg
    -0.08
    ä¸įæģ¯
    -0.08
    追éļı
    -0.07
    妻åŃIJ
    -0.07
    arih
    -0.07
    urang
    -0.07
    olumn
    -0.07
    ëĭ¥
    -0.07
    habitude
    -0.07
    POSITIVE LOGITS
    è¾Ī
    0.13
    輩
    0.10
    å¤ĸå©Ĩ
    0.10
    姥
    0.08
    åŃĻ女
    0.08
    姥çĪ·
    0.08
    udan
    0.07
    å¤ĸåħ¬
    0.07
    级
    0.07
    æħĪ祥
    0.07
    Activations Density 0.029%

    No Known Activations