© 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. 18-TRANSCODER-HP
    7. 89065
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /pp
    -0.28
    .pt
    -0.27
    oft
    -0.25
    nia
    -0.24
    lius
    -0.24
    .stub
    -0.24
    磫
    -0.23
    <Float
    -0.23
    createForm
    -0.23
    afen
    -0.23
    POSITIVE LOGITS
    chy
    0.28
     ik
    0.27
    æĺ¯æĪijçļĦ
    0.26
    éĹ´éļĻ
    0.26
    殿åłĤ
    0.26
     Yug
    0.25
     space
    0.25
     sockets
    0.25
    ichier
    0.25
     cá»ķ
    0.25
    Activations Density 0.183%

    No Known Activations

    This feature has no known activations.