© 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. 112589
    Prev
    Next
    INDEX
    Explanations

    Action words

    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
    使çĶ¨æĿĥ
    -0.25
     Scientist
    -0.23
     dissoci
    -0.23
     nou
    -0.23
    ä½į
    -0.23
     utiliz
    -0.23
    *m
    -0.22
    åĬĪ
    -0.22
    \$
    -0.22
     kettle
    -0.22
    POSITIVE LOGITS
    rise
    0.26
    æľīèī²
    0.25
    eno
    0.25
    omed
    0.25
     anonymous
    0.25
     trá»Ŀi
    0.25
    请èģĶç³»
    0.25
    oyer
    0.24
    imately
    0.24
    åħ¨èµĦ
    0.23
    Activations Density 0.003%

    No Known Activations