© 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. 140832
    Prev
    Next
    INDEX
    Explanations

    0

    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
    agg
    -0.28
    èļ¤
    -0.27
    /apache
    -0.27
    croft
    -0.25
    社
    -0.24
    ä¸Ĭä¸ĸ纪
    -0.23
     Eighth
    -0.23
     cavity
    -0.23
    avic
    -0.23
    æ±ł
    -0.23
    POSITIVE LOGITS
     embroid
    0.27
    OPSIS
    0.26
    achs
    0.25
     partially
    0.25
    æıī
    0.24
    ereum
    0.24
    lemn
    0.24
    论
    0.24
    欹
    0.23
    kind
    0.23
    Activations Density 51.826%

    No Known Activations