© 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. 6451
    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
    rophe
    -0.28
    稳
    -0.28
    ettle
    -0.26
     mou
    -0.25
     amplify
    -0.25
     speeds
    -0.24
    /power
    -0.24
    é¢Ŀå¤ĸ
    -0.24
    dense
    -0.23
    rais
    -0.23
    POSITIVE LOGITS
    ä¸ĵ家ç»Ħ
    0.26
    cek
    0.25
     Mechanics
    0.25
    oven
    0.24
    æľįä»İ
    0.24
    å®ŀæĸ½æĦıè§ģ
    0.24
    manship
    0.24
    groupid
    0.23
    VENT
    0.23
    \views
    0.23
    Activations Density 0.524%

    No Known Activations

    This feature has no known activations.