© 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. 108800
    Prev
    Next
    INDEX
    Explanations

    Technical/informational texts

    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
    herited
    -0.26
    ed
    -0.25
    ovo
    -0.25
    å¿Ĺ强
    -0.25
    Outputs
    -0.25
    entially
    -0.24
    inally
    -0.23
    æģģ
    -0.23
    alez
    -0.23
    appropri
    -0.23
    POSITIVE LOGITS
    è¨Ĺ
    0.28
     Guidance
    0.27
    tone
    0.25
    åŃļ
    0.24
    çłģ头
    0.24
    curl
    0.24
    ÅŁt
    0.24
     pm
    0.23
    çłĶ讨
    0.23
     Blast
    0.23
    Activations Density 0.269%

    No Known Activations