© 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. 12-TRANSCODER-HP
    7. 22118
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æµĬ
    -0.27
     sil
    -0.27
     drafts
    -0.26
    ught
    -0.26
    奶油
    -0.26
    -ton
    -0.25
    паÑģ
    -0.25
     arriv
    -0.25
    že
    -0.24
     perv
    -0.24
    POSITIVE LOGITS
    åĴª
    0.29
    äºij
    0.25
    ubb
    0.25
    enzie
    0.24
    undra
    0.24
    linky
    0.24
    ç®į
    0.24
     Rem
    0.24
    ICI
    0.24
    两åı¥
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.