© 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. 52799
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    -w
    -0.56
    -W
    -0.49
    wt
    -0.48
     wp
    -0.48
    ww
    -0.48
    wd
    -0.47
    wp
    -0.47
    Ws
    -0.47
    Wo
    -0.46
    ws
    -0.46
    POSITIVE LOGITS
    æģ©
    0.26
    tal
    0.26
     ten
    0.25
    åģļ人
    0.25
     Zhu
    0.25
     Richardson
    0.25
    ĥģ
    0.24
    身躯
    0.24
    htt
    0.24
    lab
    0.24
    Activations Density 0.059%

    No Known Activations