© 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. 9583
    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
    HIR
    -0.29
    hir
    -0.26
    ikip
    -0.26
    drs
    -0.25
    activex
    -0.24
    åħħåĪĨ
    -0.24
    鼶
    -0.24
    edio
    -0.24
    GridView
    -0.24
    nist
    -0.24
    POSITIVE LOGITS
    æ´±
    0.26
     cor
    0.25
     corre
    0.25
    $where
    0.25
     enclosed
    0.24
    .bel
    0.24
    ||↵
    0.24
    angkan
    0.23
     side
    0.23
     corr
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.