© 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. 9888
    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
    HTTPRequest
    -0.28
    IPP
    -0.26
     juices
    -0.25
    对æİ¥
    -0.24
     Forbidden
    -0.24
    haul
    -0.24
    isnan
    -0.24
    大åį«
    -0.24
    emen
    -0.24
    ivor
    -0.24
    POSITIVE LOGITS
     disco
    0.28
     urgent
    0.27
     pressure
    0.25
    ä¸Ģéĥ¨åĪĨ
    0.25
     belt
    0.24
    说ä»Ģä¹Ī
    0.24
    èĪī
    0.24
     dusk
    0.24
     provoked
    0.24
     fly
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.