© 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. 6181
    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
    ennis
    -0.26
    criptive
    -0.25
    óng
    -0.24
    ysz
    -0.23
    ¶Ī
    -0.23
    uiten
    -0.23
     overwritten
    -0.23
    imensional
    -0.23
    myp
    -0.23
     пÑĥÑĤ
    -0.23
    POSITIVE LOGITS
    åIJİåı°
    0.26
    ame
    0.25
    éĶĭ
    0.25
    ë²Į
    0.24
     Luk
    0.24
    è¿Ļ次
    0.24
    rike
    0.24
     alÄ±ÅŁ
    0.24
    èĥĮåIJİ
    0.24
    åīįéĿ¢
    0.24
    Activations Density 0.038%

    No Known Activations

    This feature has no known activations.