© 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. 33230
    Prev
    Next
    INDEX
    Explanations

    RNA polymerase transcription

    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
    reck
    -0.08
    å¥ĩ
    -0.08
     Nghi
    -0.07
    empo
    -0.07
    çĸ
    -0.07
    è¿IJçŃ¹
    -0.07
    å±¹
    -0.06
    å¥ĩå¼Ĥ
    -0.06
    -pill
    -0.06
    æĺİå¾·
    -0.06
    POSITIVE LOGITS
     production
    0.09
     transcription
    0.09
     Production
    0.09
    转å½ķ
    0.08
     transcript
    0.08
    Production
    0.08
    åĩºæĿ¥åIJİ
    0.07
    èįī稿
    0.07
     mRNA
    0.07
     transcripts
    0.07
    Activations Density 0.016%

    No Known Activations