© 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. 149335
    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
     plots
    -0.29
     plot
    -0.28
    ://
    -0.27
    æį·
    -0.27
    .ensure
    -0.27
    ContentSize
    -0.26
    bz
    -0.25
    iry
    -0.24
    [sub
    -0.24
     sure
    -0.24
    POSITIVE LOGITS
    pell
    0.27
    æīĢåľ¨
    0.27
    bru
    0.25
    porter
    0.25
    RuleContext
    0.24
     MenuItem
    0.24
    Prev
    0.24
    èµ·çłģ
    0.24
    好人
    0.24
    ä»»ä½ķæŶåĢĻ
    0.24
    Activations Density 1.050%

    No Known Activations

    This feature has no known activations.