© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7424
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    izedName
    -0.32
    case
    -0.29
    翼
    -0.27
    æ¢Ń
    -0.27
    壳
    -0.26
    ç¨İ
    -0.26
    cases
    -0.25
    æĬĹåĩ»
    -0.25
    åIJij
    -0.25
    /comment
    -0.25
    POSITIVE LOGITS
    æĺ´
    0.27
     sple
    0.27
    ddy
    0.27
    éĺī
    0.26
    oman
    0.26
    ancock
    0.26
    ãĥĥãĤ·
    0.25
    _Copy
    0.25
     Webcam
    0.24
    ейÑĩаÑģ
    0.24
    Activations Density 0.073%

    No Known Activations

    This feature has no known activations.