© 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. 9090
    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
    èĩ´
    -0.27
     fear
    -0.25
    append
    -0.24
    åĽłèĢĮ
    -0.24
     appended
    -0.24
    çķı
    -0.24
    åľĺ
    -0.24
    管çIJĨå·¥ä½ľ
    -0.24
     faces
    -0.24
    laws
    -0.24
    POSITIVE LOGITS
    RA
    0.28
    åĸĭ
    0.26
     Smithsonian
    0.25
    velt
    0.25
    naissance
    0.25
    çݰ代çī©æµģ
    0.25
    .ra
    0.25
    enville
    0.25
    åħĪæĬĬ
    0.25
    ahi
    0.24
    Activations Density 0.098%

    No Known Activations

    This feature has no known activations.