© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5058
    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
    ERVED
    -0.29
    zza
    -0.27
    PIO
    -0.27
    æ®ĸ
    -0.27
     inc
    -0.27
    âľį
    -0.27
    ODO
    -0.26
    åĽŀåIJĪ
    -0.25
    elu
    -0.25
    éĿ´
    -0.25
    POSITIVE LOGITS
     contracting
    0.27
    universal
    0.26
    locator
    0.25
    coni
    0.25
     Tamb
    0.25
    çķĻä¸ĭ
    0.25
    éĶ¦æłĩ
    0.25
     programme
    0.24
     Program
    0.24
    leaning
    0.24
    Activations Density 2.345%

    No Known Activations

    This feature has no known activations.