© 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. 27-TRANSCODER-HP
    7. 56376
    Prev
    Next
    INDEX
    Explanations

    scientific, medical research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çĶŁäº§èĥ½åĬĽ
    -0.29
    æ´»åĬĽ
    -0.28
    çļĦçĶŁåij½
    -0.27
    å°±è¿Ļä¹Ī
    -0.26
    çļĦ身份
    -0.26
    éĩįè¦ģåİŁåĽł
    -0.25
    ħ
    -0.25
    agt
    -0.24
    ൻ
    -0.24
    .Tree
    -0.24
    POSITIVE LOGITS
    éĹ°
    0.32
     incest
    0.28
     thicker
    0.27
    .xtext
    0.26
    /DD
    0.26
    ucken
    0.26
    è·¨
    0.25
    亳
    0.25
    éĶIJ
    0.25
    åħ³èģĶ
    0.25
    Activations Density 0.000%

    No Known Activations