© 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. 108793
    Prev
    Next
    INDEX
    Explanations

    Names in news articles

    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
    eto
    -0.30
    (False
    -0.27
     ydk
    -0.26
     False
    -0.25
    .microsoft
    -0.25
    BOOLEAN
    -0.25
     Drugs
    -0.24
    ogue
    -0.24
    itsu
    -0.24
     Heating
    -0.23
    POSITIVE LOGITS
     pure
    0.27
     leaves
    0.27
     uns
    0.26
    æ®ĭ
    0.25
    san
    0.25
     obl
    0.24
    LOS
    0.24
    åĬĽåº¦
    0.24
    è¾ĥ
    0.24
     lone
    0.24
    Activations Density 20.892%

    No Known Activations