© 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. 140835
    Prev
    Next
    INDEX
    Explanations

    warranted

    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
    æĥłåıĬ
    -0.29
    legg
    -0.26
    åĪ¤
    -0.25
    .setPrototypeOf
    -0.24
    ERIC
    -0.24
     millennium
    -0.24
    ÑĮе
    -0.24
    åį«
    -0.24
    ewhere
    -0.23
    otten
    -0.23
    POSITIVE LOGITS
    æľĢéĩįè¦ģ
    0.28
    mdi
    0.27
    æľ¬å±Ĭ
    0.25
    òn
    0.25
    æIJª
    0.25
    è¿ĺæľīä»Ģä¹Ī
    0.24
    èķŀ
    0.24
    主è¦ģåĨħ容
    0.24
    aza
    0.24
     Oc
    0.24
    Activations Density 2.097%

    No Known Activations