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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5883
    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
    è´º
    -0.28
    ä¸İæѤ
    -0.27
    WD
    -0.26
    {T
    -0.25
    Reach
    -0.25
     cad
    -0.24
     fod
    -0.24
    à¸Īำ
    -0.23
     molec
    -0.23
     Tomb
    -0.23
    POSITIVE LOGITS
    atile
    0.30
    æĭĶ
    0.29
    .between
    0.25
    æĹĭ
    0.25
    çªģ
    0.24
    çĦIJ
    0.24
    Difference
    0.24
    sson
    0.24
    裴
    0.24
     Bair
    0.24
    Activations Density 0.952%

    No Known Activations

    This feature has no known activations.