© 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. 6442
    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
    å¨ĺ
    -0.28
     tapes
    -0.27
    AMY
    -0.26
     ``(
    -0.25
    reak
    -0.24
    initely
    -0.24
    æİ¥åĬĽ
    -0.24
    ourg
    -0.24
    elta
    -0.23
    åķĨä¸ļéĵ¶è¡Į
    -0.23
    POSITIVE LOGITS
    oy
    0.26
    åĨ»
    0.26
    ugi
    0.25
    ç¥ĵ
    0.24
    说åĪ°è¿ĻéĩĮ
    0.24
     icy
    0.24
     ice
    0.23
    说åĪ°
    0.23
     ASC
    0.23
    cio
    0.23
    Activations Density 0.057%

    No Known Activations

    This feature has no known activations.