© 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. 88467
    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
     remot
    -0.26
    *</
    -0.25
     Separator
    -0.24
    hya
    -0.23
    inery
    -0.23
    atives
    -0.23
    æĦļ
    -0.23
    ography
    -0.22
     Synopsis
    -0.22
    [table
    -0.22
    POSITIVE LOGITS
     eventual
    0.26
    ãĥĥãĤ·
    0.26
    èģĶ
    0.25
    åįķä½į
    0.25
    ml
    0.24
     конкÑĥÑĢ
    0.24
     FORE
    0.24
     unit
    0.24
    REM
    0.24
    .unit
    0.23
    Activations Density 9.939%

    No Known Activations

    This feature has no known activations.