© 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. 9901
    Prev
    Next
    INDEX
    Explanations

    formal writing/discussions

    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
    apses
    -0.37
    bows
    -0.36
     fences
    -0.36
     marches
    -0.32
    usses
    -0.32
     blogs
    -0.32
     galleries
    -0.32
     buses
    -0.32
     salads
    -0.32
     caches
    -0.31
    POSITIVE LOGITS
     Altern
    0.28
    cloud
    0.28
    iar
    0.28
     altern
    0.26
    åĽº
    0.26
    altern
    0.25
    æıª
    0.25
    Cloud
    0.24
    .instant
    0.24
    Altern
    0.24
    Activations Density 0.002%

    No Known Activations