© 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. 23-TRANSCODER-HP
    7. 25626
    Prev
    Next
    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    kea
    -0.26
     dön
    -0.24
    egal
    -0.23
    ServiceImpl
    -0.23
    翻身
    -0.23
     бÑĥмаг
    -0.23
     EMC
    -0.23
    merc
    -0.23
    erc
    -0.23
    ento
    -0.23
    POSITIVE LOGITS
     alongside
    0.89
     besides
    0.84
     complement
    0.76
     additional
    0.69
    éĻ¤äºĨ
    0.68
     aside
    0.67
     beside
    0.63
     addition
    0.63
    é¢Ŀå¤ĸ
    0.62
     additionally
    0.61
    Activations Density 0.005%

    No Known Activations