© 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. 24-TRANSCODER-HP
    7. 149430
    Prev
    Next
    INDEX
    Explanations

    Varied conversational & web text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bills
    -0.29
     builder
    -0.29
     Builder
    -0.28
     builders
    -0.27
    andbox
    -0.27
    ä¹Ŀé¾Ļ
    -0.25
    -money
    -0.25
     lawful
    -0.25
    Æł
    -0.25
    bane
    -0.25
    POSITIVE LOGITS
     Conversation
    0.32
     Overview
    0.28
     look
    0.27
     conversation
    0.27
    WP
    0.27
    gee
    0.27
     sym
    0.26
     overview
    0.26
    åĢļ
    0.26
    缮
    0.26
    Activations Density 0.902%

    No Known Activations