© 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. 54833
    Prev
    Next
    INDEX
    Explanations

    Complex opinion/report texts

    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
    own
    -0.31
     Points
    -0.29
     inf
    -0.27
    缺ä¹ı
    -0.27
     points
    -0.27
    ishi
    -0.27
    ä»»
    -0.26
    çħ§
    -0.26
    Slow
    -0.26
    åĩłçĤ¹
    -0.26
    POSITIVE LOGITS
    irut
    0.31
    brero
    0.29
    datagrid
    0.28
     plaats
    0.28
    æ±Łä¸ľ
    0.28
     trimmed
    0.27
    ķĮ
    0.27
     bowls
    0.27
    éĿĴå±±
    0.26
    imuth
    0.26
    Activations Density 0.005%

    No Known Activations