© 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. 90353
    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
    orny
    -0.28
    éĿ¢ä¸´çļĦ
    -0.27
    èĻļ
    -0.26
    ano
    -0.25
    _adj
    -0.24
     implicitly
    -0.24
     Or
    -0.23
     unfortunately
    -0.23
    _INLINE
    -0.23
    amber
    -0.23
    POSITIVE LOGITS
    ittal
    0.31
    ofilm
    0.28
     Dominion
    0.27
    管çIJĨä¸Ńå¿ĥ
    0.25
    åħīçݯ
    0.24
    åĨħ容ç®Ģä»ĭ
    0.24
    ssp
    0.24
    çī¹æ´¾
    0.24
    Escort
    0.24
     enough
    0.24
    Activations Density 42.104%

    No Known Activations

    This feature has no known activations.