© 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. 6185
    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
    emann
    -0.29
    .classList
    -0.27
    iera
    -0.26
    èIJģ
    -0.25
    çIJħ
    -0.25
    åıijçĶµ
    -0.24
    ERAL
    -0.24
    趾
    -0.23
    _LOADED
    -0.23
    èªįèŃĺ
    -0.23
    POSITIVE LOGITS
    pher
    0.31
    mers
    0.30
    eva
    0.29
    éļĻ
    0.28
    æĴ¸
    0.27
    >Action
    0.25
     mù
    0.25
    æĢ»é¢Ŀ
    0.24
    lev
    0.24
    /javascript
    0.24
    Activations Density 0.200%

    No Known Activations

    This feature has no known activations.