© 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. 151412
    Prev
    Next
    INDEX
    Explanations

    technical/code-like 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
    -hearted
    -0.27
     disqualified
    -0.27
    ardin
    -0.26
     axe
    -0.26
    aupt
    -0.25
    intree
    -0.25
     discounts
    -0.24
    èµĿ
    -0.24
    axis
    -0.24
    åħ¨æĸĩ
    -0.24
    POSITIVE LOGITS
    ä¸Ŀä¸Ŀ
    0.27
    è¡£
    0.25
    .tab
    0.25
    ä¸Ģä¸Ģ
    0.25
    amon
    0.24
    æĸĻ
    0.24
    æĻºæħ§åŁİå¸Ĥ
    0.24
    opi
    0.24
    dense
    0.23
    æĹłä¸į
    0.23
    Activations Density 0.089%

    No Known Activations