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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7307
    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
    annel
    -0.31
    apest
    -0.28
    nal
    -0.27
    åĪ·
    -0.26
    -present
    -0.26
    -Sep
    -0.26
     peninsula
    -0.26
    礼
    -0.24
    \system
    -0.24
     Peninsula
    -0.24
    POSITIVE LOGITS
     classes
    0.27
    ãĤ¼
    0.26
    éı¡
    0.25
    çļĦç«ŀäºī
    0.25
     competit
    0.24
    é¹ĺ
    0.24
     regenerate
    0.24
     compet
    0.24
    èĻº
    0.24
    两åıª
    0.24
    Activations Density 1.738%

    No Known Activations

    This feature has no known activations.