© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7888
    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
    ateg
    -0.31
    entities
    -0.30
    صÙĦا
    -0.25
    çī¡
    -0.25
    _builtin
    -0.25
    etCode
    -0.25
    讹
    -0.25
    ạch
    -0.25
    ptune
    -0.24
    觯
    -0.24
    POSITIVE LOGITS
    ible
    0.27
    ãĤ¹ãĤ¿ãĥ¼ãĥĪ
    0.26
    arra
    0.24
    èĻ½
    0.24
    nings
    0.24
    CES
    0.23
    BOSE
    0.23
     sensit
    0.23
     lump
    0.23
    bole
    0.23
    Activations Density 0.145%

    No Known Activations

    This feature has no known activations.