© 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. 30-TRANSCODER-HP
    7. 95093
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    /MPL
    -0.27
     Dodge
    -0.26
    bih
    -0.26
    ayne
    -0.25
    imo
    -0.25
    .gs
    -0.25
     idols
    -0.25
    -awesome
    -0.25
    zt
    -0.25
    fm
    -0.25
    POSITIVE LOGITS
    æİīäºĨ
    0.27
     yakın
    0.27
    ity
    0.27
    ibilidad
    0.26
    åİ»åģļ
    0.26
    /full
    0.25
    ä»»
    0.25
    æİī
    0.25
    preci
    0.24
     causal
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.