© 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. 19-TRANSCODER-HP
    7. 8385
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Decision
    -0.32
    Decision
    -0.28
    åĨ³çŃĸ
    -0.28
    _decision
    -0.27
    decision
    -0.27
     üzerine
    -0.25
    (Arrays
    -0.25
     concentr
    -0.24
    çĻ½ç³ĸ
    -0.24
     Mount
    -0.23
    POSITIVE LOGITS
     welcome
    0.29
     arb
    0.26
    -neutral
    0.25
    æĶ¾å¿ĥ
    0.24
    éĢłç¦ı
    0.24
    ditor
    0.24
    驼
    0.24
    èħ¾
    0.24
     medial
    0.23
     lump
    0.23
    Activations Density 0.411%

    No Known Activations

    This feature has no known activations.