© 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. 30-TRANSCODER-HP
    7. 97046
    Prev
    Next
    INDEX
    Explanations

    science and engineering

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    NotFoundError
    -0.28
     sank
    -0.27
    @Module
    -0.27
     depress
    -0.26
    ointment
    -0.25
    æĿĵ
    -0.25
    å®ļçĤ¹
    -0.25
    代åĬŀ
    -0.25
    avings
    -0.25
     Shaft
    -0.25
    POSITIVE LOGITS
     robotics
    0.34
    çĶŁçī©åѦ
    0.33
     engineering
    0.32
     science
    0.31
     STEM
    0.31
    çĶŁçī©ç§ijæĬĢ
    0.31
     Neuroscience
    0.30
    ç§ijæĬĢ
    0.30
    Robot
    0.30
     Science
    0.30
    Activations Density 0.887%

    No Known Activations