© 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. 56696
    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
    Not in Any Lists

    No Comments

    Negative Logits
    .Ignore
    -0.30
    åģĩ
    -0.28
    others
    -0.28
     ent
    -0.27
     vac
    -0.27
    åģĩ设
    -0.27
    kov
    -0.26
     others
    -0.26
    ä¸įçĶ¨
    -0.26
    æĹłéľĢ
    -0.26
    POSITIVE LOGITS
    ä¹ĭ称
    0.27
    æŃ»äºĨ
    0.27
     modeling
    0.26
    æľī幸
    0.26
    ETA
    0.25
     optim
    0.25
     Modeling
    0.25
    éĢĢè¿ĺ
    0.24
    :model
    0.24
     modelos
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.