© 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. 142599
    Prev
    Next
    INDEX
    Explanations

    department

    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
     dd
    -0.28
    айн
    -0.27
    (dd
    -0.27
    aydın
    -0.27
    å°ģ
    -0.25
    尤为éĩįè¦ģ
    -0.24
     gag
    -0.24
    -dd
    -0.24
    漤
    -0.23
    ä½Ĩåį´
    -0.23
    POSITIVE LOGITS
     bowls
    0.28
     disput
    0.27
    uez
    0.25
    buffers
    0.24
    饴
    0.24
    PEG
    0.24
    volatile
    0.24
    ела
    0.23
    产éĶĢ
    0.23
    agate
    0.23
    Activations Density 51.883%

    No Known Activations