© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 90235
    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
    Negative Logits
    sold
    -0.26
    ⽩
    -0.25
     unfavor
    -0.25
     interact
    -0.25
    çļ´
    -0.24
    Accessory
    -0.24
    çĺ¦
    -0.24
    :?
    -0.24
    Topology
    -0.24
     VOID
    -0.24
    POSITIVE LOGITS
    etics
    0.28
    á»Ĩ
    0.27
    ervised
    0.26
    iej
    0.26
    ucht
    0.26
    æĻĶ
    0.26
    è¡Ĺ
    0.26
     quick
    0.26
     Earlier
    0.25
     Incorpor
    0.25
    Activations Density 7.495%

    No Known Activations

    This feature has no known activations.