© 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. 106924
    Prev
    Next
    INDEX
    Explanations

    scientific analysis

    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
     Serialize
    -0.30
    QL
    -0.26
    serialize
    -0.26
    .Handler
    -0.26
     Gray
    -0.26
     serialize
    -0.26
     sanitizer
    -0.26
    sweet
    -0.26
     Shutterstock
    -0.26
    Serialize
    -0.26
    POSITIVE LOGITS
    æĮģ
    0.33
    èĩªèº«
    0.29
     biom
    0.29
     biology
    0.29
    entions
    0.27
    ifs
    0.26
     synthesis
    0.26
     vehicles
    0.26
     videos
    0.26
    oli
    0.25
    Activations Density 1.118%

    No Known Activations