© 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. 1791
    Prev
    Next
    INDEX
    Explanations

    gene functions and implications

    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
     indes
    -0.06
    åĬłäºĨ
    -0.06
     queued
    -0.06
    ersonic
    -0.06
    è§ĦåĪĻ
    -0.06
    æ··åIJĪ
    -0.06
    æĹłè¾¹
    -0.06
     prepared
    -0.06
    alma
    -0.06
     flavored
    -0.06
    POSITIVE LOGITS
     genes
    0.12
    åŁºåĽłçļĦ
    0.10
    ç¼ĸçłģ
    0.09
     coding
    0.08
     encoding
    0.08
     implicated
    0.08
     pathways
    0.08
     gene
    0.08
     functions
    0.08
     names
    0.08
    Activations Density 0.607%

    No Known Activations