© 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. 12-TRANSCODER-HP
    7. 22115
    Prev
    Next
    INDEX
    Explanations

    Eco

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     competition
    -0.32
    olo
    -0.27
    Compet
    -0.26
    鸡汤
    -0.26
    积水
    -0.26
     competitor
    -0.26
     competency
    -0.26
    åİĺ
    -0.26
    渴
    -0.25
     Competition
    -0.25
    POSITIVE LOGITS
     environmentally
    0.32
    /cop
    0.31
    çݯä¿Ŀ
    0.30
    çģŃ
    0.30
    rase
    0.28
    æ¶Ī
    0.26
    çĨĦ
    0.26
    ingleton
    0.26
     pledges
    0.26
    loff
    0.26
    Activations Density 0.000%

    No Known Activations