© 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. 52874
    Prev
    Next
    INDEX
    Explanations

    Emissions and pollution

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éĩį
    -0.34
    _boxes
    -0.26
    éĹ´éļĻ
    -0.25
    éģ½
    -0.25
    orama
    -0.25
    edException
    -0.25
    éĩįä¸Ń
    -0.25
    ades
    -0.25
    intern
    -0.24
    _blocks
    -0.24
    POSITIVE LOGITS
    .getRaw
    0.28
    è´¥
    0.27
     decay
    0.27
    elia
    0.26
    ech
    0.26
     impacts
    0.25
    elow
    0.25
    æķĹ
    0.25
    .production
    0.25
    /raw
    0.25
    Activations Density 0.011%

    No Known Activations