© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64067
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    è¿ĩ大
    -0.32
    è¿ĩäºİ
    -0.28
    missing
    -0.27
    bery
    -0.26
    rary
    -0.26
    _^(
    -0.26
    ç¥ģ
    -0.26
    ãi
    -0.25
    缺ä¹ı
    -0.25
    ):(
    -0.25
    POSITIVE LOGITS
    åħį
    0.38
     cleanly
    0.29
     only
    0.28
    ermann
    0.28
    à¹Ģà¸Ĺ
    0.27
     moderate
    0.27
    natural
    0.27
    èĩªçĦ¶
    0.26
     natural
    0.26
    leon
    0.26
    Activations Density 82.435%

    No Known Activations