© 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. 23-TRANSCODER-HP
    7. 25380
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Heck
    -0.25
     desar
    -0.24
    cons
    -0.24
     tóc
    -0.24
    broadcast
    -0.23
     Authority
    -0.23
     Collapse
    -0.23
    ",'
    -0.23
    crawl
    -0.23
    èµ°
    -0.23
    POSITIVE LOGITS
    ary
    0.30
    åı¦ä¸Ģè¾¹
    0.28
    æµĶ
    0.26
    æķ°ç»Ħ
    0.26
     quoting
    0.25
    ibble
    0.25
    jin
    0.25
    umbing
    0.25
    ancode
    0.24
    (cin
    0.24
    Activations Density 0.007%

    No Known Activations

    This feature has no known activations.