© 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. 8812
    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
     Income
    -0.27
     emph
    -0.26
     humili
    -0.25
    >:</
    -0.24
    ï¼ļ%
    -0.24
    æ³£
    -0.24
    .assertThat
    -0.24
    æŃ£å¸¸ä½¿çĶ¨
    -0.24
    åĬŁçĶ¨
    -0.24
    éĽĮ
    -0.23
    POSITIVE LOGITS
     supers
    0.32
    vers
    0.30
    éĻIJå®ļ
    0.29
    TOR
    0.28
    antine
    0.27
    terms
    0.26
    rente
    0.26
    mand
    0.25
    admin
    0.25
    stant
    0.25
    Activations Density 0.818%

    No Known Activations

    This feature has no known activations.