© 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. 41084
    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
    çĩİ
    -0.28
    pac
    -0.26
    豫
    -0.25
    çł£
    -0.25
     Prairie
    -0.24
    ))-
    -0.24
    å®ŀè´¨æĢ§
    -0.24
    lassen
    -0.24
    лад
    -0.24
     dela
    -0.23
    POSITIVE LOGITS
    çĸı
    0.29
    <?↵
    0.29
    _PB
    0.27
    ç³ĸ
    0.26
    wk
    0.26
    ä¸įåħĭ
    0.26
    ÑĦин
    0.25
    aks
    0.25
    äsent
    0.24
    row
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.