© 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. 56385
    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
    _suite
    -0.28
    roys
    -0.26
     lia
    -0.25
     urge
    -0.25
     Ont
    -0.24
    rys
    -0.24
    .toInt
    -0.24
    riers
    -0.24
    æŀ§
    -0.24
    bia
    -0.23
    POSITIVE LOGITS
    ç¶ĵçĩŁ
    0.27
     ksztaÅĤ
    0.27
    nut
    0.26
    лан
    0.26
     observations
    0.25
     Bolton
    0.25
     Anchor
    0.25
    rophic
    0.25
     Obs
    0.24
    Anchor
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.