© 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. 14-TRANSCODER-HP
    7. 41607
    Prev
    Next
    INDEX
    Explanations

    cheek

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     vertically
    -0.29
     nett
    -0.26
    æŃ£æĸĩ
    -0.26
     buddies
    -0.26
    æĢİä¹Īçľĭ
    -0.25
     Faces
    -0.24
    ystack
    -0.24
    Faces
    -0.24
     kans
    -0.24
    éĽĢ
    -0.24
    POSITIVE LOGITS
    å¡ij
    0.31
     Ultra
    0.27
    seau
    0.25
    ::__
    0.25
    onal
    0.25
     Rhe
    0.24
     remake
    0.23
    å°±æĬĬ
    0.23
    ä¹ĭæīĢ以
    0.23
    èĢĮè¿Ļ
    0.23
    Activations Density 1.699%

    No Known Activations