© 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. 32-TRANSCODER-HP
    7. 40834
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    otic
    -0.29
    .pad
    -0.26
    ennon
    -0.26
    _ped
    -0.26
    Bring
    -0.25
    åIJĮæĥħ
    -0.25
    otine
    -0.25
    åĽŀé¦Ī
    -0.24
    rito
    -0.24
    ulia
    -0.24
    POSITIVE LOGITS
    款
    0.30
    äºĭåIJİ
    0.28
    AFX
    0.27
    PLAIN
    0.27
    agne
    0.26
    审
    0.26
    viz
    0.25
    åıĤ
    0.25
     ÑģоÑģед
    0.25
    .bukkit
    0.25
    Activations Density 0.002%

    No Known Activations