© 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. 88691
    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
     alb
    -0.32
     Gall
    -0.30
    alom
    -0.25
    好人
    -0.25
    β
    -0.24
    AtPath
    -0.24
     allot
    -0.24
    affiliate
    -0.23
    tractive
    -0.23
    ignon
    -0.23
    POSITIVE LOGITS
    ä»°
    0.26
    俯
    0.26
    .codehaus
    0.25
    ä¿ĥ
    0.25
     toward
    0.24
    /example
    0.24
    ooter
    0.24
    UEL
    0.23
     Committee
    0.23
    TEE
    0.23
    Activations Density 0.891%

    No Known Activations

    This feature has no known activations.