© 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. 42371
    Prev
    Next
    INDEX
    Explanations

    subordinates, child

    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
    ank
    -0.08
     Bauer
    -0.06
    itas
    -0.06
     hon
    -0.06
    ky
    -0.06
    è¾Ĺ转
    -0.06
    zen
    -0.06
    èĩªè¨Ģèĩªè¯Ń
    -0.06
    leftrightarrow
    -0.06
    /cache
    -0.05
    POSITIVE LOGITS
    ynd
    0.09
    éĢģä¸Ģ
    0.08
    åĪĨæĶ¯
    0.08
    ragt
    0.08
    åĪĨæĭħ
    0.08
    CHILD
    0.08
    -done
    0.08
    headed
    0.08
    ×ľ×ª
    0.08
    缴æİ¥è¿Ľåħ¥
    0.08
    Activations Density 0.030%

    No Known Activations