© 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. 151406
    Prev
    Next
    INDEX
    Explanations

    Articles and technical documents

    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
    ç«ĭãģ¦
    -0.33
    cycl
    -0.31
    伦çIJĨ
    -0.29
     Eth
    -0.29
    Eth
    -0.28
    åIJĪ
    -0.28
     eth
    -0.27
    ç«ĭ
    -0.27
    oppers
    -0.25
     lul
    -0.25
    POSITIVE LOGITS
    ardy
    0.31
     stakes
    0.28
    agues
    0.26
    furt
    0.26
    èĿ®
    0.25
    BuildContext
    0.25
    TOOLS
    0.25
    åıijå±ķæľºéģĩ
    0.25
    stadt
    0.25
     stake
    0.24
    Activations Density 0.105%

    No Known Activations