© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129490
    Prev
    Next
    INDEX
    Explanations

    Dates or date ranges

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ovic
    -0.27
    agy
    -0.27
     iso
    -0.25
     freelance
    -0.25
    ohen
    -0.25
    .gs
    -0.24
    nez
    -0.24
    isters
    -0.24
    .gg
    -0.24
     traffic
    -0.23
    POSITIVE LOGITS
    åı¦ä¸Ģè¾¹
    0.29
    åı¦ä¸Ģæĸ¹éĿ¢
    0.27
    oklyn
    0.27
     McConnell
    0.25
    åĪĿåĪĽ
    0.25
    Defaults
    0.25
    ched
    0.25
    èĪĮå°ĸ
    0.25
    iences
    0.24
     accordingly
    0.24
    Activations Density 0.002%

    No Known Activations