© 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. 9-TRANSCODER-HP
    7. 29213
    Prev
    Next
    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    äºĨåIJ§
    -0.25
    ipes
    -0.24
     econ
    -0.24
    èī²ç´ł
    -0.24
    yle
    -0.23
    uno
    -0.23
     strained
    -0.23
    ine
    -0.23
     eval
    -0.22
     Forg
    -0.22
    POSITIVE LOGITS
    åĵĨ
    0.30
    tré
    0.28
    åĪĨå·¥
    0.27
    esium
    0.24
    fois
    0.24
    æĭħ
    0.23
    åħ¨åľº
    0.23
    endum
    0.23
    reet
    0.23
    adecimal
    0.23
    Activations Density 2.166%

    No Known Activations