© 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. 23-TRANSCODER-HP
    7. 25552
    Prev
    Next
    INDEX
    Explanations

    file data/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Shoe
    -0.26
    çķĶ
    -0.24
     Spare
    -0.24
     telesc
    -0.24
    iales
    -0.23
     genomes
    -0.23
    itaire
    -0.23
    daq
    -0.23
     Serie
    -0.23
    ickey
    -0.23
    POSITIVE LOGITS
    undy
    0.28
    -mouth
    0.27
     lord
    0.27
    ertz
    0.27
    mob
    0.27
    osition
    0.27
    x
    0.26
    åıªæĢķ
    0.25
    ram
    0.25
    le
    0.25
    Activations Density 0.213%

    No Known Activations