© 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. 41554
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    ivated
    -0.27
    backs
    -0.27
    STEM
    -0.27
    warts
    -0.27
    FN
    -0.26
    oming
    -0.26
    åıijæĮ¥
    -0.25
    TES
    -0.25
    à¦ĸ
    -0.25
    WN
    -0.24
    POSITIVE LOGITS
    åħ¨åijĺ
    0.30
    enha
    0.28
    idor
    0.25
    çŃ·
    0.25
    软
    0.25
    ç´§æĢ¥
    0.24
    edium
    0.24
    个交æĺĵ
    0.24
     terminal
    0.24
    æ¶īåıĬåĪ°
    0.24
    Activations Density 2.258%

    No Known Activations