© 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. 30254
    Prev
    Next
    INDEX
    Explanations

    precision

    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
    åIJİèĢħ
    -0.31
    桧
    -0.31
    atan
    -0.30
    antine
    -0.28
    arian
    -0.28
    innen
    -0.26
    饲åħ»
    -0.26
    rier
    -0.26
    sing
    -0.25
    ing
    -0.25
    POSITIVE LOGITS
    åĬłå¯Ĩ
    0.32
    warts
    0.28
    .Sdk
    0.26
    第ä¸Ģ书记
    0.25
    hash
    0.25
    åĽĬ
    0.25
     modele
    0.24
    enos
    0.24
    -hash
    0.24
    ToProps
    0.24
    Activations Density 3.907%

    No Known Activations