© 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. 90352
    Prev
    Next
    INDEX
    Explanations

    "Lev" or "lev" substring

    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
    eturn
    -0.28
    crew
    -0.28
    ä¾Ŀèµĸ
    -0.27
    ocks
    -0.26
     unp
    -0.25
    ãģĭãģijãģ¦
    -0.24
    ãģĭãģij
    -0.24
     outs
    -0.24
    ãĤĦãģ£ãģ¦
    -0.24
    .SaveChanges
    -0.23
    POSITIVE LOGITS
    gua
    0.28
     Hundred
    0.28
    HIP
    0.25
    稳
    0.25
    VEL
    0.25
    å¤§åĽ½
    0.24
     vibration
    0.24
    bial
    0.24
    iate
    0.24
    dig
    0.24
    Activations Density 2.034%

    No Known Activations