© 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. 131139
    Prev
    Next
    INDEX
    Explanations

    unusual characters

    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
    Äķ
    -0.28
    ersistence
    -0.26
    ejs
    -0.25
     edm
    -0.25
    è¿ŀç»Ń
    -0.25
    Sharper
    -0.24
    uhn
    -0.23
     Eis
    -0.23
    .dds
    -0.23
     Shay
    -0.23
    POSITIVE LOGITS
     coll
    0.27
     guess
    0.25
    _unicode
    0.25
     flying
    0.25
     subject
    0.24
    ç°¿
    0.24
     =
    0.23
    ìŀIJê°Ģ
    0.23
    /~
    0.23
    夸
    0.23
    Activations Density 42.402%

    No Known Activations