© 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. 49246
    Prev
    Next
    INDEX
    Explanations

    shared or connecting units

    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
    çIJĨ论水平
    -0.07
    ekom
    -0.07
    æĬ¥æ¡Ī
    -0.07
    è¿Ļçķª
    -0.06
    çĻ»å½ķåIJİ
    -0.06
    缸è¾ħ缸æĪIJ
    -0.06
    æīĢ欲è¨Ģ
    -0.06
     glas
    -0.06
    Align
    -0.06
    ç§įç§į
    -0.06
    POSITIVE LOGITS
    shared
    0.12
     shared
    0.12
    /shared
    0.11
    åħ±äº«
    0.11
    -between
    0.10
    connecting
    0.10
     Shared
    0.10
    (shared
    0.10
    åħ¶éĹ´
    0.10
    -shared
    0.09
    Activations Density 0.009%

    No Known Activations