© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63495
    Prev
    Next
    INDEX
    Explanations

    margin properties/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
    Not in Any Lists

    No Comments

    Negative Logits
    åIJĦåĮº
    -0.28
    ç£ķ
    -0.25
    tical
    -0.25
    Spawn
    -0.24
    inati
    -0.24
    ongs
    -0.23
    æŀ¶åŃIJ
    -0.23
    æ¶īåıĬ
    -0.23
    await
    -0.23
    lbrace
    -0.23
    POSITIVE LOGITS
    olum
    0.24
    ained
    0.24
     reduced
    0.23
    æĪĸèĢħæĺ¯
    0.23
    isten
    0.23
    ClickListener
    0.23
    çĽĤ
    0.23
    å®ļæŶ
    0.22
    ä¸įè´Ł
    0.22
    ors
    0.22
    Activations Density 1.931%

    No Known Activations