© 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. 8001
    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
    amen
    -0.29
    请æĤ¨
    -0.29
    /wait
    -0.26
    俸
    -0.26
    tok
    -0.26
    èĥĻ
    -0.26
     qualifications
    -0.26
    vtk
    -0.25
    Treatment
    -0.25
    建
    -0.24
    POSITIVE LOGITS
    æ¶ī
    0.29
    æķ£
    0.27
    Verified
    0.25
    rides
    0.25
    ãĥªãĥ¼
    0.25
    赤
    0.24
    etr
    0.24
     kir
    0.24
    å¨ħ
    0.24
    asurement
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.