© 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. 6227
    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
     Visible
    -0.26
    yal
    -0.26
     visible
    -0.25
     competition
    -0.25
     annex
    -0.25
    ëĬIJ
    -0.24
    çĤĻ
    -0.24
    bras
    -0.24
     branching
    -0.24
     natural
    -0.24
    POSITIVE LOGITS
    iteDatabase
    0.27
    ucceed
    0.26
    ilio
    0.25
    ç´ĢéĮĦ
    0.24
    лиÑĤ
    0.24
    ISTR
    0.23
    çĬģ
    0.23
    ç½Ħ
    0.23
     outFile
    0.23
    ç¾İæľ¯é¦Ĩ
    0.23
    Activations Density 0.530%

    No Known Activations

    This feature has no known activations.