© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 86758
    Prev
    Next
    INDEX
    Explanations

    code or configuration snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    stead
    -0.28
    ä¹ĭä½Ļ
    -0.24
    geführt
    -0.24
    说æľį
    -0.24
    åħļåĴĮ
    -0.24
    éĩijå¸ģ
    -0.24
    setVisibility
    -0.24
    invisible
    -0.24
    ='_
    -0.23
    èµĦäº§è´ŁåĢº
    -0.23
    POSITIVE LOGITS
    åĪĴ
    0.32
    åĬĥ
    0.27
    -front
    0.27
     deem
    0.25
    ooting
    0.25
    å±ķå¼Ģ
    0.25
     DUP
    0.25
    åİ»
    0.24
     Stress
    0.24
     volunteering
    0.24
    Activations Density 0.006%

    No Known Activations