© 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. 108647
    Prev
    Next
    INDEX
    Explanations

    The

    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
    otech
    -0.27
     ли
    -0.26
    olec
    -0.26
    -rule
    -0.24
    å¡ĺ
    -0.24
    rear
    -0.24
    -interest
    -0.23
    assin
    -0.23
    Monitor
    -0.23
    å²Ń
    -0.23
    POSITIVE LOGITS
    ALES
    0.28
    Templates
    0.26
    äºĴ
    0.25
    Gam
    0.25
    çľĭä½ł
    0.25
    æĬķ
    0.25
    çıij
    0.24
     osp
    0.24
    plates
    0.24
    æĭįçħ§
    0.24
    Activations Density 25.305%

    No Known Activations