© 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. 97551
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ½Ķ
    -0.27
    ylene
    -0.27
     Äijiá»ĥn
    -0.26
    客æĪ·æıIJä¾Ľ
    -0.24
    lesia
    -0.23
    .showMessage
    -0.23
    ÑĤоп
    -0.23
    館
    -0.23
    rapper
    -0.23
     STM
    -0.23
    POSITIVE LOGITS
     trái
    0.28
     shell
    0.27
    ij
    0.27
    lat
    0.26
    shell
    0.26
    hi
    0.26
    ug
    0.26
    ugh
    0.25
    aut
    0.25
    ck
    0.25
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.