© 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. 4953
    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
    ium
    -0.30
    oko
    -0.29
    ent
    -0.29
    ici
    -0.28
    icer
    -0.28
    rophe
    -0.27
    emouth
    -0.24
    oter
    -0.24
    ining
    -0.24
    amics
    -0.24
    POSITIVE LOGITS
    pull
    0.27
    .prevent
    0.27
     Cheer
    0.25
    åĬŁ
    0.25
    Ứ
    0.24
    åĬĽè¿ĺæĺ¯
    0.24
    åŃĺåľ¨
    0.23
    cac
    0.23
    æĹ¥çĶµ
    0.23
    ä»Ĭ天çļĦ
    0.23
    Activations Density 1.239%

    No Known Activations

    This feature has no known activations.