© 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. 22183
    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
    为é¦ĸçļĦ
    -0.28
    éŀł
    -0.28
     Gur
    -0.28
    ledged
    -0.26
    eled
    -0.25
    äu
    -0.25
    çĸı导
    -0.25
    ter
    -0.25
    éļ¶å±ŀäºİ
    -0.25
    齿
    -0.24
    POSITIVE LOGITS
     tiên
    0.29
    chio
    0.28
    scopes
    0.28
    stuff
    0.27
     volume
    0.27
    Volume
    0.26
     IPT
    0.25
     viz
    0.25
    Temporary
    0.25
    scope
    0.24
    Activations Density 0.000%

    No Known Activations