© 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. 140809
    Prev
    Next
    INDEX
    Explanations

    variety of topics

    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
    ä»ĬçĶŁ
    -0.29
    ious
    -0.26
    ates
    -0.26
    iesen
    -0.25
    çīĪæľ¬
    -0.25
    &W
    -0.25
     ATK
    -0.25
     Pittsburgh
    -0.24
    ewing
    -0.24
    ãģĨ
    -0.23
    POSITIVE LOGITS
    Php
    0.28
    ç²ī
    0.27
    åģ¶çĦ¶
    0.26
    çªį
    0.25
    endforeach
    0.25
    泡泡
    0.24
    }//
    0.24
    çĶ»å®¶
    0.24
    SOAP
    0.24
    æ³¢
    0.24
    Activations Density 7.659%

    No Known Activations