© 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. 60701
    Prev
    Next
    INDEX
    Explanations

    supporting and containing parts

    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
    yfik
    -0.07
    çĦ¶å¤§
    -0.07
    天ä¸ĭ
    -0.07
    STM
    -0.07
    è¿Ļ个æĹ¶ä»£
    -0.06
    :normal
    -0.06
    åĨįè§ģ
    -0.06
    chia
    -0.06
     circol
    -0.06
    besch
    -0.06
    POSITIVE LOGITS
     containing
    0.20
    带çĿĢ
    0.19
     carrying
    0.16
     contenant
    0.16
    è¿ŀåIJĮ
    0.15
    帶èijĹ
    0.15
    带æľī
    0.14
    åIJ«æľī
    0.14
    æIJºå¸¦
    0.14
    æī¿è½½çĿĢ
    0.13
    Activations Density 0.448%

    No Known Activations