© 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. 4885
    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
     qual
    -0.28
     verg
    -0.27
    Qual
    -0.27
    éĦĻ
    -0.26
    owie
    -0.25
    amed
    -0.25
    warts
    -0.25
    èµĦæł¼
    -0.25
    æĭĽæĬķæłĩ
    -0.24
    resco
    -0.24
    POSITIVE LOGITS
     transfers
    0.28
    seek
    0.28
    éĴ´
    0.26
    侬
    0.26
    ettle
    0.26
    OfString
    0.25
    ximity
    0.24
    çĥ§
    0.24
     sovereign
    0.24
     Cooper
    0.24
    Activations Density 0.016%

    No Known Activations

    This feature has no known activations.