© 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. 29219
    Prev
    Next
    INDEX
    Explanations

    bring

    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
    士
    -0.29
    éĤ¦
    -0.29
    fuel
    -0.27
     munch
    -0.26
    menus
    -0.25
    IXEL
    -0.25
    ä»Ļ
    -0.24
    สà¸ĩ
    -0.24
    åħį
    -0.24
    ancel
    -0.24
    POSITIVE LOGITS
    nid
    0.28
    泺
    0.27
     subject
    0.26
    enko
    0.26
    .Flat
    0.26
    ailable
    0.26
    éĻĦ件
    0.26
    etry
    0.25
    ake
    0.25
    subject
    0.24
    Activations Density 1.075%

    No Known Activations