© 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. 88149
    Prev
    Next
    INDEX
    Explanations

    Names Floyd, Ferguson

    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
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.30
    åijĬè¯ī她
    -0.30
    ÑĢеб
    -0.27
    éĥ½è¯´
    -0.27
    她说
    -0.27
    æĥij
    -0.26
     Dia
    -0.25
    大家åĪĨ享
    -0.25
    ä»ĸ说
    -0.24
    ãģ«ãĤĪ
    -0.24
    POSITIVE LOGITS
    顶
    0.27
     Koch
    0.25
    åıĸ
    0.24
    idity
    0.24
     Vision
    0.23
     weekly
    0.23
    darwin
    0.23
    çŃ¾åIJį
    0.23
    charm
    0.23
     nomin
    0.23
    Activations Density 6.533%

    No Known Activations