© 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. 33-TRANSCODER-HP
    7. 52690
    Prev
    Next
    INDEX
    Explanations

    technical or scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    emen
    -0.29
    oli
    -0.27
    MING
    -0.26
     o
    -0.26
    ement
    -0.25
    绯
    -0.25
    æī¾
    -0.24
     Overs
    -0.24
    eting
    -0.24
    .pe
    -0.24
    POSITIVE LOGITS
    åĿĩçĶ±
    0.29
    åıªåī©ä¸ĭ
    0.28
    ä¸ĢæĬĬ
    0.27
    duk
    0.27
    -plugins
    0.26
    ä¿Ŀ驾
    0.26
    -append
    0.25
    ä¸įåħĭ
    0.25
    éĢŀ
    0.25
    .createClass
    0.25
    Activations Density 0.025%

    No Known Activations