© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 24-TRANSCODER-HP
    7. 150706
    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
    <Pair
    -0.28
    éħIJ
    -0.26
    .tie
    -0.26
    æ·±åĮĸ
    -0.26
     ull
    -0.25
    _elim
    -0.24
    goods
    -0.24
    ybrid
    -0.23
    imore
    -0.23
    åī©
    -0.23
    POSITIVE LOGITS
    æĪijä»¬çŁ¥éģĵ
    0.26
    å°ģ
    0.26
    LError
    0.25
     Sk
    0.25
     Dr
    0.25
     Vib
    0.24
    æľīæĦı
    0.24
    omer
    0.24
    gence
    0.24
     Hipp
    0.24
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.