© 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. 62648
    Prev
    Next
    INDEX
    Explanations

    pockets

    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
    让çĶ¨æĪ·
    -0.27
     Conway
    -0.27
     trụ
    -0.26
    ullen
    -0.26
    noc
    -0.24
     HPV
    -0.24
     alone
    -0.24
    çĭ¬èĩª
    -0.24
    ulu
    -0.24
     hawk
    -0.23
    POSITIVE LOGITS
    chia
    0.26
    主ä¹īèĢħ
    0.25
    curities
    0.25
    è¿Ŀ
    0.25
    (SIG
    0.24
    ecz
    0.24
    senal
    0.23
    iez
    0.23
    nesc
    0.23
    æIJģ
    0.23
    Activations Density 4.779%

    No Known Activations