© 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. 64291
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical language

    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
     vej
    -0.29
    æ°ijæĹı
    -0.27
    reck
    -0.25
    raith
    -0.25
    ä¸Ģå°ģä¿¡
    -0.24
    yps
    -0.24
    cheng
    -0.23
    äºĨåIJĹ
    -0.23
    å°±ä¸įä¼ļ
    -0.23
    ä¹Łä¸įä¼ļ
    -0.23
    POSITIVE LOGITS
    èĩ¾
    0.27
    EF
    0.25
     EF
    0.25
    inand
    0.25
     meanwhile
    0.25
    ubar
    0.24
    çĮĬ
    0.24
    ESCO
    0.23
    DF
    0.23
    ä¸Ńæĸ¹
    0.23
    Activations Density 1.923%

    No Known Activations