© 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. 7644
    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
    æīĭåĬ¿
    -0.28
     keyst
    -0.26
    (Table
    -0.25
    梳
    -0.25
     real
    -0.24
     inorder
    -0.24
    Document
    -0.24
     faux
    -0.24
     Scre
    -0.24
    æĪijå¦Ī
    -0.24
    POSITIVE LOGITS
    inding
    0.29
    è¿Ļè¾¹
    0.27
    anging
    0.26
     Abby
    0.26
    ignet
    0.26
     Affairs
    0.26
    åĿ»
    0.26
    .dy
    0.24
    grown
    0.24
    ijn
    0.24
    Activations Density 0.909%

    No Known Activations

    This feature has no known activations.