© 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. 4688
    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
    æµģ转
    -0.27
     commerce
    -0.26
    ÑĢод
    -0.25
    Undo
    -0.24
    undo
    -0.24
    çݰ代社ä¼ļ
    -0.24
    å±¥è¡Į
    -0.23
    movie
    -0.23
    çŁŃçŁŃ
    -0.23
    ик
    -0.23
    POSITIVE LOGITS
    FETCH
    0.27
    drs
    0.27
     Www
    0.25
    iset
    0.25
    ForEach
    0.25
    symbol
    0.24
    annon
    0.24
    immers
    0.24
    hips
    0.24
    onen
    0.23
    Activations Density 0.156%

    No Known Activations

    This feature has no known activations.