© 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. 142507
    Prev
    Next
    INDEX
    Explanations

    Web content snippets

    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
    Negative Logits
    XM
    -0.28
     SMP
    -0.27
     setImage
    -0.26
    å¸ĪåĤħ
    -0.26
    -Sah
    -0.25
    æĻĭæ±Ł
    -0.25
    ç£Ļ
    -0.24
    (phase
    -0.24
    ç¤ģ
    -0.24
    /DD
    -0.24
    POSITIVE LOGITS
     Cum
    0.28
    åѦ
    0.27
    .digital
    0.25
    anders
    0.25
    opoulos
    0.24
    unix
    0.24
    minute
    0.24
    isp
    0.24
    arium
    0.23
    åį°
    0.23
    Activations Density 40.075%

    No Known Activations