© 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. 7679
    Prev
    Next
    INDEX
    Explanations

    Landscaping and architecture

    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
    s
    -0.25
     Extras
    -0.25
    pent
    -0.25
    ettings
    -0.25
    dge
    -0.25
    proved
    -0.25
     appare
    -0.24
    æĪĺçķ¥æĢ§
    -0.24
    讲
    -0.24
    mens
    -0.23
    POSITIVE LOGITS
     borders
    0.28
     Layer
    0.27
    Layer
    0.26
    èIJĭ
    0.26
     substr
    0.26
    Layers
    0.26
    _LAYER
    0.26
    _CSR
    0.25
    çľīæ¯Ľ
    0.24
     layer
    0.24
    Activations Density 0.011%

    No Known Activations