© 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. 129645
    Prev
    Next
    INDEX
    Explanations

    Medical/scientific writing

    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
    çļĦ好
    -0.27
    BR
    -0.26
     pens
    -0.25
    ä½Ļ
    -0.25
    .br
    -0.25
    Dev
    -0.25
    entai
    -0.25
     blanks
    -0.25
    tees
    -0.24
     forks
    -0.24
    POSITIVE LOGITS
    adget
    0.32
    rove
    0.29
    culus
    0.28
    erior
    0.26
    æĬ¥å¤į
    0.24
    æľŁ
    0.24
    以ä¸ĬçļĦ
    0.24
    ĮĢ
    0.24
    rastructure
    0.23
    å²Ľä¸Ĭ
    0.23
    Activations Density 0.107%

    No Known Activations