© 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. 27-TRANSCODER-HP
    7. 7689
    Prev
    Next
    INDEX
    Explanations

    Code and technical snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    uale
    -0.32
     Bud
    -0.31
     bud
    -0.29
    wo
    -0.27
    åĶ®
    -0.27
    åĩ¡
    -0.26
    sla
    -0.26
     ju
    -0.26
    hu
    -0.25
    æĤī
    -0.25
    POSITIVE LOGITS
     sensed
    0.30
    iran
    0.28
    åŀł
    0.26
    æĦŁ
    0.26
     JpaRepository
    0.25
    _Size
    0.25
    itten
    0.25
    utters
    0.25
     voiced
    0.25
    iginal
    0.24
    Activations Density 0.008%

    No Known Activations