© 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. 41677
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing

    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
    åħ¨æĻ¯
    -0.30
     normals
    -0.28
    åľĪåŃIJ
    -0.28
     visual
    -0.27
     Visual
    -0.25
    족
    -0.25
    uras
    -0.25
    Visual
    -0.24
    ometers
    -0.24
     quir
    -0.24
    POSITIVE LOGITS
    à¤Ŀ
    0.31
    é«ĺä»·
    0.28
    èmes
    0.26
    çĪ±ä¸Ĭ
    0.25
    -online
    0.25
     lives
    0.24
     Lives
    0.24
    athe
    0.24
     wherever
    0.24
    orum
    0.24
    Activations Density 0.060%

    No Known Activations