© 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. 7583
    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
     KsiÄĻ
    -0.28
    ä¹Ŀé¾Ļ
    -0.26
    åıªçŁ¥éģĵ
    -0.26
    ä¸ĬçıŃ
    -0.25
    rium
    -0.25
    责任å¿ĥ
    -0.24
     doorstep
    -0.24
     Seasons
    -0.24
    åľĪ
    -0.23
    éĵĹ
    -0.23
    POSITIVE LOGITS
    uzzi
    0.31
    eph
    0.30
    å¸Į
    0.29
    é¹ĺ
    0.25
    çĩĥ
    0.25
     Through
    0.25
     Conduct
    0.25
    thermal
    0.25
    窣
    0.24
     Tie
    0.24
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.