© 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. 108382
    Prev
    Next
    INDEX
    Explanations

    Atmosphere/Environment

    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
    ibal
    -0.28
    ؤÙĪÙĦ
    -0.27
    èѦ
    -0.27
    è¡·
    -0.26
     tend
    -0.26
    æĸ°éĹ»è®°èĢħ
    -0.26
    è¿Ļ两年
    -0.26
    ä¸įå¦Ĥ
    -0.25
    åĪĨå±Ģ
    -0.25
    Ø´ÙĤ
    -0.25
    POSITIVE LOGITS
    å¼ģ
    0.29
     essentials
    0.27
    éĩį
    0.27
     skeleton
    0.24
    éĹ°
    0.24
    åıĪ
    0.24
    anitize
    0.23
     dial
    0.23
     bikini
    0.23
    è·¨
    0.23
    Activations Density 19.765%

    No Known Activations