© 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. 8184
    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
    ç½®
    -0.32
    ogui
    -0.28
    大éĩı
    -0.28
    å²Ń
    -0.28
    缮
    -0.28
    rips
    -0.27
     koÅĦ
    -0.27
    幸
    -0.26
    olina
    -0.25
    rem
    -0.25
    POSITIVE LOGITS
     Jur
    0.32
     XL
    0.28
    омеÑĢ
    0.28
    Ỽ
    0.28
    thers
    0.27
     Shade
    0.26
    RunWith
    0.26
    Everyone
    0.26
    æĶ»åĿļ
    0.25
     jur
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.