© 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. 18-TRANSCODER-HP
    7. 90141
    Prev
    Next
    INDEX
    Explanations

    Commentary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    canf
    -0.25
    å°Ĭ严
    -0.25
     illeg
    -0.25
    morgan
    -0.24
    积累
    -0.24
    æī¿æĭħ责任
    -0.24
    _membership
    -0.24
    éļ¾è¿ĩ
    -0.24
    奸
    -0.24
    nett
    -0.24
    POSITIVE LOGITS
    roid
    0.27
    è¿Ļä¹Ī说
    0.27
    UIT
    0.27
    åħ¹
    0.24
     Libraries
    0.23
    çĶµåĬ¨
    0.23
    roids
    0.23
     sóc
    0.23
    quate
    0.23
    (func
    0.23
    Activations Density 9.810%

    No Known Activations