© 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. 20-TRANSCODER-HP
    7. 129087
    Prev
    Next
    INDEX
    Explanations

    databases, software, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bucket
    -0.27
    ç»Ń约
    -0.26
    orest
    -0.25
    ientos
    -0.24
    çľģæķĻèĤ²åİħ
    -0.24
    çĩĴ
    -0.23
    约åIJĪ
    -0.23
    æĿŁ
    -0.23
    çĥ§
    -0.23
    è¥Ħ
    -0.23
    POSITIVE LOGITS
    ä¸Ģ份
    0.29
    åıĸæ¶Ī
    0.27
    ance
    0.26
    arent
    0.26
        ↵    ↵    ↵    ↵
    0.25
    c
    0.25
    –
    0.25
    edium
    0.24
    inson
    0.24
    coc
    0.24
    Activations Density 17.647%

    No Known Activations