© 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. 19-TRANSCODER-HP
    7. 9521
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĨ¨
    -0.30
    scopes
    -0.28
    ç¿»
    -0.27
     rigor
    -0.26
    dux
    -0.25
    specifier
    -0.25
    çĸ²
    -0.24
     dep
    -0.24
    ç½²
    -0.24
    .scope
    -0.24
    POSITIVE LOGITS
    æıIJåįĩ
    0.27
    _utilities
    0.25
     masks
    0.25
     crawling
    0.24
    _xt
    0.24
    pain
    0.24
    .servers
    0.23
    .SOCK
    0.23
     masked
    0.23
     Others
    0.23
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.