© 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. 27-TRANSCODER-HP
    7. 58608
    Prev
    Next
    INDEX
    Explanations

    Code-related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĢļéģĵ
    -0.33
     vale
    -0.26
    plet
    -0.26
    Occurred
    -0.26
    .*/↵
    -0.25
    appen
    -0.25
     Loch
    -0.24
     impost
    -0.24
    ceiver
    -0.24
    adget
    -0.24
    POSITIVE LOGITS
    guns
    0.28
     way
    0.27
    à¸Ķร
    0.27
    éŃĶ鬼
    0.25
    (Constructor
    0.25
     Manufacturer
    0.24
     manufacturers
    0.24
    rarian
    0.24
    åµĩ
    0.24
    æĸĭ
    0.24
    Activations Density 0.002%

    No Known Activations