© 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. 62567
    Prev
    Next
    INDEX
    Explanations

    neuroscience

    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
    _FF
    -0.25
    ä»Ģ麽
    -0.25
    她æĺ¯
    -0.25
     PARTY
    -0.24
    伺
    -0.24
    åIJĦæł·
    -0.24
    æł·
    -0.24
    èĩªå·±
    -0.24
    .party
    -0.23
    磼
    -0.23
    POSITIVE LOGITS
    ponential
    0.27
    è»Ł
    0.25
    ooks
    0.24
    çĮ¶
    0.24
    arp
    0.24
    -road
    0.24
    fol
    0.24
    itle
    0.24
    豨
    0.23
     Chick
    0.23
    Activations Density 3.042%

    No Known Activations