© 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. 31-TRANSCODER-HP
    7. 17974
    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_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éŨå¤ĸ
    -0.28
     acrylic
    -0.26
    link
    -0.26
    yscale
    -0.25
    纶
    -0.24
    ound
    -0.24
    vard
    -0.24
    项
    -0.23
     mi
    -0.23
     turnaround
    -0.23
    POSITIVE LOGITS
    bish
    0.31
    деÑģÑı
    0.26
    erval
    0.26
    /Home
    0.25
     Morm
    0.25
    isty
    0.25
    åĨ³å®ļ
    0.25
    -Mobile
    0.25
    å¼Ĥ
    0.25
    enment
    0.24
    Activations Density 0.001%

    No Known Activations