© 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. 90123
    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
    IH
    -0.28
    [:,:
    -0.25
    >\↵
    -0.25
    çļĦä¼ĺçĤ¹
    -0.25
    èĩªçĦ¶èĢĮçĦ¶
    -0.24
    æŃ£å¸¸çļĦ
    -0.23
    ç»ı
    -0.23
    好äºĨ
    -0.23
    ynthesis
    -0.23
    .FromResult
    -0.23
    POSITIVE LOGITS
     hooks
    0.26
    SETTING
    0.25
    cott
    0.25
    óst
    0.24
    rone
    0.24
    åı©
    0.24
     Establish
    0.24
    -setting
    0.24
    untime
    0.24
    lotte
    0.24
    Activations Density 16.872%

    No Known Activations

    This feature has no known activations.