© 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. 20-TRANSCODER-HP
    7. 142440
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pha
    -0.31
    AtA
    -0.28
    orsi
    -0.26
    akest
    -0.25
    pcf
    -0.24
     Abed
    -0.24
    IPH
    -0.24
    aned
    -0.24
    足迹
    -0.24
     Destruction
    -0.23
    POSITIVE LOGITS
     investigator
    0.27
    iros
    0.27
     institution
    0.25
    Brief
    0.25
     watches
    0.25
    enh
    0.25
     tempor
    0.25
     WATCH
    0.24
    ac
    0.24
    æľīçļĦ
    0.24
    Activations Density 32.542%

    No Known Activations

    This feature has no known activations.