© 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. 24-TRANSCODER-HP
    7. 151284
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     wx
    -0.29
    ED
    -0.28
     slack
    -0.27
    wx
    -0.26
    WX
    -0.25
    edith
    -0.25
    æļĤç¼ĵ
    -0.25
    çĢijå¸ĥ
    -0.25
    WH
    -0.24
    WHO
    -0.24
    POSITIVE LOGITS
    .struct
    0.34
    acker
    0.32
    structuring
    0.30
    Defs
    0.29
    structures
    0.27
     structures
    0.27
     regimes
    0.26
    identified
    0.26
    åĪ¶
    0.25
    statements
    0.25
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.