© 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. 30301
    Prev
    Next
    INDEX
    Explanations

    part codes

    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
     padd
    -0.28
     subpoena
    -0.28
    imson
    -0.26
    éĵ¤
    -0.26
    Msp
    -0.25
    haft
    -0.25
    åijIJ
    -0.25
    onso
    -0.25
    aldi
    -0.25
     McGu
    -0.24
    POSITIVE LOGITS
    åºĬ
    0.32
     bed
    0.27
    cir
    0.27
    ç»ıèIJ¥æ´»åĬ¨
    0.27
    eller
    0.27
    æķ¢
    0.24
     beds
    0.24
     Cir
    0.24
     Rhe
    0.24
     contrary
    0.23
    Activations Density 0.241%

    No Known Activations