© 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. 129251
    Prev
    Next
    INDEX
    Explanations

    my

    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
    ·»
    -0.28
    身
    -0.26
    arend
    -0.25
    äºĭçī©
    -0.25
    Ñģол
    -0.25
    大éģĵ
    -0.24
    .CV
    -0.24
    çķĻä¸ĭ
    -0.24
    cales
    -0.23
    icals
    -0.23
    POSITIVE LOGITS
    Subset
    0.27
    æĮĩ导æĦıè§ģ
    0.26
    agrid
    0.26
    éĺ»åĬĽ
    0.26
    _FACTORY
    0.25
     response
    0.25
    ByUrl
    0.25
    ä¸į足以
    0.24
    çĵ´
    0.24
     Broadcast
    0.24
    Activations Density 39.096%

    No Known Activations