© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7253
    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
     Closure
    -0.28
    closure
    -0.27
    /mail
    -0.26
    Rail
    -0.25
    inary
    -0.25
    åĮħ容
    -0.25
    ubbles
    -0.25
    Closure
    -0.25
    losures
    -0.24
    recursive
    -0.24
    POSITIVE LOGITS
     vents
    0.30
    hos
    0.29
     vent
    0.29
    vent
    0.28
    Vent
    0.28
     displacement
    0.28
     tors
    0.27
    æİ¥åĪ°
    0.27
    æķĮ
    0.26
     disorder
    0.25
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.