© 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. 25-TRANSCODER-HP
    7. 109357
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dimensions
    -0.27
    avia
    -0.26
    ersistence
    -0.26
    çĵľ
    -0.26
     reput
    -0.25
    æŀģåĵģ
    -0.25
    yt
    -0.24
    SubMenu
    -0.24
    "${
    -0.24
     trap
    -0.24
    POSITIVE LOGITS
    æĢ»æĺ¯
    0.28
     touched
    0.27
    æľ¬æĸĩ
    0.27
    åĺĺ
    0.26
     YYS
    0.25
    æĸĩä¸Ń
    0.25
    çī¹åĪ«å£°æĺİ
    0.25
    æīij
    0.24
    åĥı
    0.24
    论
    0.24
    Activations Density 0.128%

    No Known Activations