© 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. 8238
    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
    ä»ĸå°±
    -0.31
    æĸŁ
    -0.28
    çļ±
    -0.27
    oling
    -0.25
     stake
    -0.25
     stav
    -0.25
    ¡
    -0.25
    ä¸įæĥľ
    -0.24
    æµģåĬ¨
    -0.24
     Fun
    -0.24
    POSITIVE LOGITS
    sort
    0.32
    çł»
    0.28
    kaar
    0.27
     sort
    0.26
    纶
    0.26
    agher
    0.26
    orio
    0.25
     gsi
    0.25
    emma
    0.24
    edm
    0.24
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.