© 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. 9669
    Prev
    Next
    INDEX
    Explanations

    metro

    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
    æĢı
    -0.30
    ides
    -0.28
    FileSync
    -0.28
    æľ¨è´¨
    -0.28
    âľĸ
    -0.27
    åıĮèĦļ
    -0.26
    è¢ħ
    -0.26
    åħįè²»
    -0.26
    æ¡Ĩæŀ¶åįıè®®
    -0.26
    æľ¨
    -0.25
    POSITIVE LOGITS
     ldb
    0.28
    èģĶç³»
    0.27
    .bs
    0.27
    cbd
    0.26
    imity
    0.26
    cce
    0.25
    åij¨åĽ´
    0.25
    cité
    0.25
     interconnected
    0.25
     ban
    0.25
    Activations Density 0.007%

    No Known Activations