© 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. 4826
    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
    idon
    -0.30
    æĥħ
    -0.27
    cams
    -0.27
     Impl
    -0.26
    åIJĮèĥŀ
    -0.25
    åı¸æľº
    -0.25
    ifth
    -0.24
     Gonzalez
    -0.24
    åīįæīĢ
    -0.24
    æĪĪ
    -0.24
    POSITIVE LOGITS
     fragile
    0.30
     universal
    0.29
     age
    0.28
     fragmented
    0.28
     yield
    0.27
    å¯ĮåĬĽ
    0.27
    Fragment
    0.26
    åħ¥åѦ
    0.26
     locally
    0.26
     vibr
    0.26
    Activations Density 0.043%

    No Known Activations

    This feature has no known activations.