© 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. 41531
    Prev
    Next
    INDEX
    Explanations

    Code, copyright, or Patrick's day

    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
     зÑĢениÑı
    -0.27
    (conv
    -0.27
    å¢ĥçķĮ
    -0.26
    ç«łç¨ĭ
    -0.25
    çļĦåŁİå¸Ĥ
    -0.24
     Ñģебе
    -0.24
     eslint
    -0.24
    iego
    -0.24
    |#
    -0.24
    (lr
    -0.24
    POSITIVE LOGITS
    ingly
    0.32
    CP
    0.30
    antly
    0.29
     CPA
    0.28
     CP
    0.28
    åħĥ
    0.27
     Crunch
    0.27
    èĪī
    0.25
    CG
    0.25
    CF
    0.25
    Activations Density 0.130%

    No Known Activations