© 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. 129026
    Prev
    Next
    INDEX
    Explanations

    since

    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
    åĴĮåľ°åĮº
    -0.29
    hack
    -0.28
    责任æĦŁ
    -0.28
    åĴĮåıijå±ķ
    -0.27
    ikes
    -0.26
    åħįè²»
    -0.26
    _constraint
    -0.25
    å¥ĺ
    -0.25
    ically
    -0.25
    ively
    -0.25
    POSITIVE LOGITS
    ampo
    0.31
    orias
    0.29
    漫
    0.27
    mpr
    0.26
    TestClass
    0.25
    æľŁéĹ´
    0.25
     chiar
    0.25
    .bat
    0.24
    yh
    0.24
    bac
    0.24
    Activations Density 14.988%

    No Known Activations