© 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. 18-TRANSCODER-HP
    7. 90231
    Prev
    Next
    INDEX
    Explanations

    Start of lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     nú
    -0.25
     springs
    -0.25
    wave
    -0.24
     xnxx
    -0.24
    硬
    -0.24
     Spicer
    -0.24
    æİ¥åIJ¬
    -0.24
    /render
    -0.23
    çĿ«æ¯Ľ
    -0.23
    erp
    -0.23
    POSITIVE LOGITS
     upt
    0.28
     plan
    0.27
    ourg
    0.25
     conc
    0.25
    两级
    0.25
    å¹ķ
    0.25
     setError
    0.24
    aus
    0.24
    æĬ¤èĤ¤
    0.23
     Plan
    0.23
    Activations Density 4.509%

    No Known Activations