© 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. 7736
    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
    rox
    -0.29
    .ibatis
    -0.27
    ç«Ł
    -0.25
    assed
    -0.24
    artial
    -0.24
    abb
    -0.24
    对æѤ
    -0.24
    箦
    -0.23
     borderRadius
    -0.23
     Mt
    -0.23
    POSITIVE LOGITS
    æľīä»·åĢ¼
    0.27
     Examiner
    0.26
    cuts
    0.25
    egra
    0.25
    isoft
    0.24
    ıģı
    0.24
    æľīä»·åĢ¼çļĦ
    0.24
    ivation
    0.23
    itizer
    0.23
    ivate
    0.22
    Activations Density 0.080%

    No Known Activations

    This feature has no known activations.