© 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. 6592
    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
     Antar
    -0.31
    èĻļ空
    -0.26
    许
    -0.26
     thereafter
    -0.26
    lags
    -0.26
    ãģªãģĦãĤĪãģĨãģ«
    -0.25
    SystemService
    -0.25
     Opport
    -0.25
    ullet
    -0.24
    許
    -0.24
    POSITIVE LOGITS
     allev
    0.31
    iras
    0.31
     meaning
    0.30
    çĶ¨äºİ
    0.28
     accommod
    0.28
    ç¼Ŀ
    0.27
    ali
    0.27
    readcrumbs
    0.26
    places
    0.25
    ae
    0.25
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.