© 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. 41689
    Prev
    Next
    INDEX
    Explanations

    impress

    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
    æħķ
    -0.27
    utive
    -0.27
    tical
    -0.25
    ä»
    -0.25
     Major
    -0.24
     conf
    -0.24
     Maj
    -0.24
    aken
    -0.24
    .Builder
    -0.24
     major
    -0.23
    POSITIVE LOGITS
    èĿĩ
    0.29
    飫
    0.28
    holm
    0.27
    æĦıåij³çĿĢ
    0.27
    女主
    0.27
    æĻķ
    0.26
    vasion
    0.26
    _ve
    0.25
    é£ŀè·ĥ
    0.25
     <=>
    0.24
    Activations Density 0.749%

    No Known Activations