© 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. 18000
    Prev
    Next
    INDEX
    Explanations

    product advertisement suggestions

    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
     BORDER
    -0.30
    arrow
    -0.29
     border
    -0.27
     Arrow
    -0.26
    å¹³åı°
    -0.26
    DL
    -0.26
    稿
    -0.25
     Fischer
    -0.24
    _pdata
    -0.24
     serializers
    -0.24
    POSITIVE LOGITS
    warts
    0.31
     consistent
    0.28
    _advanced
    0.27
    /interface
    0.26
     consistency
    0.26
    consistent
    0.26
    itol
    0.26
    ibi
    0.25
    壯
    0.25
    ritz
    0.25
    Activations Density 11.557%

    No Known Activations