© 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. 88243
    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
    Textures
    -0.27
    以åħ¶
    -0.26
     unresolved
    -0.25
    çīĪæĿĥå½ĴåİŁ
    -0.25
    .ImageField
    -0.25
     rematch
    -0.25
     trumpet
    -0.24
    è´¨
    -0.24
    resolve
    -0.24
    .react
    -0.24
    POSITIVE LOGITS
    积æŀģæĢ§
    0.33
     Inv
    0.27
     BI
    0.26
    ento
    0.26
    -inv
    0.25
    æ·»
    0.25
    izations
    0.25
     Wa
    0.24
    Inv
    0.24
    ож
    0.24
    Activations Density 48.480%

    No Known Activations

    This feature has no known activations.