© 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. 19827
    Prev
    Next
    INDEX
    Explanations

    2

    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
     Gutenberg
    -0.27
    entity
    -0.26
    addin
    -0.26
    antt
    -0.26
    oleon
    -0.25
    çĶľçĶľ
    -0.25
    äºĭåħĪ
    -0.25
    blas
    -0.25
     backlash
    -0.24
    ä»Ĩ
    -0.24
    POSITIVE LOGITS
    ons
    0.28
    ones
    0.28
    åı
    0.27
    åĺĺ
    0.26
    岿
    0.26
    åĽŀåĽ½
    0.26
    dio
    0.25
    icit
    0.25
    çľĭä»ĸ
    0.25
     Mos
    0.24
    Activations Density 0.140%

    No Known Activations