© 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. 151120
    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
    Not in Any Lists

    No Comments

    Negative Logits
     QIcon
    -0.29
     trail
    -0.28
     Trail
    -0.28
    Trail
    -0.26
     trails
    -0.26
     Marker
    -0.25
    .Generation
    -0.25
    Extension
    -0.25
    Rua
    -0.25
    apsed
    -0.25
    POSITIVE LOGITS
    åħ±é¸£
    0.29
    stärke
    0.28
     imperson
    0.26
     rhyme
    0.25
    itsu
    0.25
     backing
    0.25
    istance
    0.24
    nish
    0.24
     resonance
    0.24
    esson
    0.23
    Activations Density 0.896%

    No Known Activations

    This feature has no known activations.