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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4816
    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
    iously
    -0.31
    PPER
    -0.29
    iosis
    -0.28
    igkeit
    -0.27
    ials
    -0.27
    noinspection
    -0.26
    çĦ¶åIJİ
    -0.26
    ovable
    -0.26
    Cow
    -0.26
    lio
    -0.25
    POSITIVE LOGITS
    åĴı
    0.28
    åĢŃ
    0.27
     operand
    0.27
     LU
    0.27
     deut
    0.27
    详ç»ĨäºĨ解
    0.25
     footing
    0.25
    åºĶå½ĵ
    0.24
     iceberg
    0.24
    _________________↵↵
    0.23
    Activations Density 0.009%

    No Known Activations

    This feature has no known activations.