© 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. 64799
    Prev
    Next
    INDEX
    Explanations

    Code/technical text

    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
    çĥĬ
    -0.25
     davon
    -0.24
    -prefix
    -0.24
    finity
    -0.24
     screen
    -0.24
     erw
    -0.24
    æĸĽ
    -0.24
    inent
    -0.23
    -reply
    -0.23
     familiar
    -0.23
    POSITIVE LOGITS
    Bloc
    0.29
     MPS
    0.27
    minimal
    0.27
    yne
    0.27
    åĿĹ
    0.27
    港
    0.26
    .nodeType
    0.26
     march
    0.25
     incremental
    0.25
    archical
    0.25
    Activations Density 30.039%

    No Known Activations