© 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. 4729
    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
    IPH
    -0.28
    ä¸Ģç¯ĩ
    -0.27
    unken
    -0.26
    æĹħ
    -0.26
    imenti
    -0.26
    æĹ¢
    -0.25
    .undefined
    -0.24
    å¾Īæ·±
    -0.24
    éķĸ
    -0.24
    æ»Ķ
    -0.24
    POSITIVE LOGITS
     owe
    0.28
    isque
    0.25
    agger
    0.24
     cast
    0.24
    coal
    0.23
     owes
    0.23
    ZX
    0.23
    oter
    0.23
     casts
    0.23
    ession
    0.22
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.