© 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. 7171
    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
    IMATE
    -0.30
     hi
    -0.29
    ftar
    -0.28
     sok
    -0.27
     availability
    -0.27
     hyper
    -0.27
    hyper
    -0.26
    hi
    -0.26
    imate
    -0.26
    availability
    -0.25
    POSITIVE LOGITS
    à¤Ŀ
    0.28
    è°Ķ
    0.27
    åĽŀæĶ¶
    0.26
    鼾
    0.26
    å°ĨæĿ¥
    0.25
    влек
    0.25
    .compare
    0.24
    ylie
    0.24
     cục
    0.24
     past
    0.24
    Activations Density 0.401%

    No Known Activations

    This feature has no known activations.