© 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. 27133
    Prev
    Next
    INDEX
    Explanations

    chemical synthesis intermediates

    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
    amac
    -0.06
    _COMPLEX
    -0.06
    ape
    -0.06
    Pods
    -0.06
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.06
    lis
    -0.06
    دÙģ
    -0.06
    åIJİèħ¿
    -0.06
    าà¸Ķ
    -0.06
    ¼Ī
    -0.06
    POSITIVE LOGITS
    æĹ¢æľī
    0.09
     versus
    0.08
    _[
    0.07
    æľīä½ķ
    0.07
    缸è¾ĥäºİ
    0.07
     vs
    0.07
     BOTH
    0.07
    resti
    0.07
    quo
    0.07
    åĪ°ä»Ģä¹Ī
    0.07
    Activations Density 0.004%

    No Known Activations