© 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. 7616
    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
     Fort
    -0.25
    æľªæĪIJ
    -0.25
    çĤİ
    -0.24
    äºŃ
    -0.24
     Vuex
    -0.24
    rieve
    -0.24
    éģĩéļ¾
    -0.24
    жи
    -0.24
     av
    -0.23
    inic
    -0.23
    POSITIVE LOGITS
    å±İ
    0.27
    contro
    0.27
     collaboration
    0.26
    好åIJĹ
    0.25
    hazi
    0.25
    fal
    0.25
    å°¾
    0.25
    ãĥIJãĥ«
    0.25
    åģļåĪ°äºĨ
    0.25
    Absolutely
    0.25
    Activations Density 1.652%

    No Known Activations

    This feature has no known activations.