© 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. 27-TRANSCODER-HP
    7. 58527
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Resume
    -0.25
    sein
    -0.25
     Bend
    -0.25
     sheets
    -0.25
    -cross
    -0.24
    opol
    -0.24
    Speed
    -0.24
     nab
    -0.24
     bend
    -0.24
    ]=='
    -0.24
    POSITIVE LOGITS
    olean
    0.29
     Pvt
    0.27
    åij½ä»¤
    0.27
    çĶŁæ´»æĸ¹å¼ı
    0.27
    å±Ģåī¯å±Ģéķ¿
    0.26
    agraph
    0.25
    ctor
    0.25
    ffects
    0.24
     reactionary
    0.24
    ftware
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.