© 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. 19-TRANSCODER-HP
    7. 7980
    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
     Limit
    -0.25
    çł»
    -0.25
    åıĺå¾ĹæĽ´åĬł
    -0.24
    æĦıæĥ³ä¸įåĪ°
    -0.24
    CreateInfo
    -0.24
    ainers
    -0.24
     Revel
    -0.24
     foreseeable
    -0.23
     bonded
    -0.23
    plat
    -0.23
    POSITIVE LOGITS
    fa
    0.33
    cul
    0.29
    lâ
    0.27
    æĸĩåĮĸçļĦ
    0.25
    no
    0.25
     kms
    0.25
    fas
    0.25
    çİ°
    0.25
    è¿ĻäºĽäºº
    0.25
    exact
    0.25
    Activations Density 0.019%

    No Known Activations

    This feature has no known activations.