© 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. 89407
    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
    terminal
    -0.27
    éĩįè¦ģæĮĩ示
    -0.27
    éĢł
    -0.27
    交代
    -0.26
     terminal
    -0.26
    -sn
    -0.26
     Fitz
    -0.26
     bbw
    -0.25
     dependent
    -0.25
     VIS
    -0.25
    POSITIVE LOGITS
    unte
    0.25
    èľľ
    0.25
    eler
    0.25
    nze
    0.25
    JM
    0.25
    åįıä½ľ
    0.25
    ieron
    0.25
     Shoe
    0.24
    asin
    0.24
    å¿į
    0.24
    Activations Density 1.124%

    No Known Activations

    This feature has no known activations.