© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9308
    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
    绳
    -0.27
    ching
    -0.27
    enting
    -0.27
    imes
    -0.26
    åĩłåı¥
    -0.26
    contre
    -0.25
    ialog
    -0.25
    ablish
    -0.25
     Owned
    -0.24
    gı
    -0.24
    POSITIVE LOGITS
    ôn
    0.27
    驱
    0.26
    éļı
    0.25
    /native
    0.24
    DR
    0.24
    ame
    0.24
    æ±Ĺ
    0.24
     inverted
    0.24
    ynamodb
    0.24
    ama
    0.23
    Activations Density 0.570%

    No Known Activations

    This feature has no known activations.