© 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. 142776
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
     whichever
    -0.30
    åĪĹåĩº
    -0.29
    кÑĥлÑĮÑĤÑĥÑĢ
    -0.27
    icina
    -0.26
    çļĦåĵģçīĮ
    -0.26
    ина
    -0.25
    ieten
    -0.24
    ineTransform
    -0.24
    缪
    -0.24
    .bc
    -0.24
    POSITIVE LOGITS
     stand
    0.31
    æ¦ľ
    0.29
    æģķ
    0.28
    rim
    0.27
    çĥĤ
    0.26
    ators
    0.26
     stop
    0.26
    ibbon
    0.26
     st
    0.25
    lap
    0.25
    Activations Density 17.855%

    No Known Activations