© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89646
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ETO
    -0.29
    regor
    -0.28
     onResponse
    -0.28
    rtle
    -0.28
    ilated
    -0.27
    rosso
    -0.27
     moden
    -0.26
    .LENGTH
    -0.26
    lke
    -0.25
     doorstep
    -0.25
    POSITIVE LOGITS
     prev
    0.29
    enes
    0.28
     sup
    0.28
    ниÑĨа
    0.28
     ch
    0.28
     clar
    0.27
     fil
    0.27
     saf
    0.27
     lan
    0.26
    irt
    0.26
    Activations Density 2.749%

    No Known Activations

    This feature has no known activations.