© 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. 6694
    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
    anos
    -0.28
    æ¤ħåŃIJ
    -0.27
     due
    -0.25
    ipline
    -0.25
    èµ°åľ¨
    -0.24
    due
    -0.24
    ombs
    -0.24
    rob
    -0.24
     titular
    -0.24
    çĶ±äºİ
    -0.23
    POSITIVE LOGITS
    塵
    0.26
     Opposition
    0.25
    å½ĵæĻļ
    0.25
    å°ĺ
    0.24
     opposition
    0.24
    quip
    0.24
    EEP
    0.23
    ardu
    0.23
    第ä¸īèĢħ
    0.23
    айн
    0.23
    Activations Density 0.120%

    No Known Activations

    This feature has no known activations.