© 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. 30417
    Prev
    Next
    INDEX
    Explanations

    ended

    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
    æĬ½æŁ¥
    -0.27
     caul
    -0.27
    .qual
    -0.26
     lesser
    -0.24
    .Short
    -0.24
     Short
    -0.24
    ä¾Ŀ
    -0.24
    .Pe
    -0.24
     Scar
    -0.23
    é¢ij
    -0.23
    POSITIVE LOGITS
    æ´¹
    0.26
    ãĥĩãĥ³
    0.26
     $?
    0.25
    riculum
    0.24
    exion
    0.24
    orgh
    0.24
    ä»ĺ
    0.23
     denom
    0.23
    ä»ĺãģij
    0.23
    lijk
    0.23
    Activations Density 1.518%

    No Known Activations