© 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. 20-TRANSCODER-HP
    7. 140904
    Prev
    Next
    INDEX
    Explanations

    Excerpts from various documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ķĮ
    -0.32
     simply
    -0.31
    æł¹æľ¬å°±ä¸į
    -0.30
     пÑĢоÑģÑĤо
    -0.28
     coinc
    -0.27
     coincide
    -0.27
     frankly
    -0.25
    .Sequential
    -0.25
     outright
    -0.24
    æł¹æľ¬ä¸į
    -0.24
    POSITIVE LOGITS
     sometimes
    0.54
    æľīæŶ
    0.49
    æľīæŶåĢĻ
    0.46
     Sometimes
    0.44
    sometimes
    0.42
    å¾Īå¤ļæŶåĢĻ
    0.40
    Sometimes
    0.39
     mostly
    0.36
     often
    0.35
    æŁIJäºĽ
    0.35
    Activations Density 82.699%

    No Known Activations