© 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. 23546
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    æĭĵ
    -0.25
    æĿ¿
    -0.24
     correct
    -0.24
    upid
    -0.24
    oba
    -0.24
    gon
    -0.24
    inden
    -0.24
    /slick
    -0.23
    .defaults
    -0.23
     ado
    -0.23
    POSITIVE LOGITS
     furthermore
    0.35
     moreover
    0.33
    ä¸Ķ
    0.32
    Furthermore
    0.32
    Moreover
    0.30
    表æĺİ
    0.29
    Interestingly
    0.29
    åħ¶ä¸Ńæľī
    0.28
    èĢĮä¸Ķ
    0.28
     Furthermore
    0.28
    Activations Density 0.024%

    No Known Activations