© 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. 20-TRANSCODER-HP
    7. 142727
    Prev
    Next
    INDEX
    Explanations

    used

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    FML
    -0.29
    åŃĹ符
    -0.27
    unan
    -0.27
    omers
    -0.26
    perate
    -0.26
    ENCH
    -0.26
    opers
    -0.25
    omo
    -0.25
    chner
    -0.25
    æĪª
    -0.25
    POSITIVE LOGITS
    å¯Ĵ
    0.26
    eed
    0.26
    igr
    0.26
    è°¨
    0.26
    alse
    0.25
     tat
    0.25
    .ms
    0.25
    æ°Ķ温
    0.24
    ea
    0.24
     continuity
    0.24
    Activations Density 7.180%

    No Known Activations