© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4924
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĢ¾æĸľ
    -0.28
    enga
    -0.28
    cade
    -0.28
    bearing
    -0.27
    кÑĢÑĥÑĤ
    -0.26
    æĸĩæĺĮ
    -0.25
    eneg
    -0.24
    otional
    -0.24
    Ãģ
    -0.24
     close
    -0.24
    POSITIVE LOGITS
    les
    0.31
    ebb
    0.28
    (act
    0.26
     getInput
    0.25
    strt
    0.25
     percentages
    0.24
    /rss
    0.24
     beneficiary
    0.24
    饮éħĴ
    0.23
    .selector
    0.23
    Activations Density 0.016%

    No Known Activations