© 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. 9865
    Prev
    Next
    INDEX
    Explanations

    scientific/technical language

    np_max-act-logits · gemini-2.0-flash
    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
    oppel
    -0.32
    heel
    -0.28
    istance
    -0.27
    odes
    -0.26
    atories
    -0.25
    inson
    -0.25
    ethyst
    -0.25
     `[
    -0.25
    avorite
    -0.25
    acement
    -0.24
    POSITIVE LOGITS
    sol
    0.32
    /H
    0.30
    gas
    0.28
    service
    0.27
    /O
    0.27
     sol
    0.26
    /M
    0.26
    °
    0.26
    /N
    0.26
    /P
    0.26
    Activations Density 0.048%

    No Known Activations