© 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. 32-TRANSCODER-HP
    7. 44072
    Prev
    Next
    INDEX
    Explanations

    CAD software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åİŁè°ħ
    -0.29
    åİŁæĸĩåľ°åĿĢ
    -0.28
    technology
    -0.28
     rootView
    -0.27
    lds
    -0.27
     TECHNO
    -0.27
     Technology
    -0.26
     stro
    -0.25
     pul
    -0.25
     technology
    -0.25
    POSITIVE LOGITS
    icers
    0.25
     neut
    0.25
    /widget
    0.25
    ivent
    0.24
    (MPI
    0.24
    è¹Ħ
    0.23
    ä¹Ļæĸ¹
    0.23
    çļĦæĥħ
    0.23
     Bett
    0.23
    éĻįèIJ½
    0.23
    Activations Density 0.006%

    No Known Activations