© 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. 88997
    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
    .Export
    -0.26
    hread
    -0.26
    çļİ
    -0.25
    agara
    -0.25
    éķ¿éķ¿
    -0.24
    oord
    -0.24
    å¨ĺ
    -0.24
    aya
    -0.24
     Export
    -0.24
    ह
    -0.24
    POSITIVE LOGITS
    å®Įç»ĵ
    0.25
     future
    0.25
    xbd
    0.25
     Units
    0.24
    ãĤ¢ãĤ¦ãĥĪ
    0.24
    .statusText
    0.24
    容å¿į
    0.24
    åħij
    0.24
    Inc
    0.24
    ceÄŁi
    0.24
    Activations Density 3.341%

    No Known Activations

    This feature has no known activations.