© 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. 22-TRANSCODER-HP
    7. 111124
    Prev
    Next
    INDEX
    Explanations

    website content/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Quote
    -0.28
    AINED
    -0.26
    è¿Ľ
    -0.25
    Rib
    -0.25
     seals
    -0.24
    ick
    -0.24
     naming
    -0.24
    inery
    -0.24
    민
    -0.23
    plies
    -0.23
    POSITIVE LOGITS
    -Smith
    0.27
    phis
    0.26
    arg
    0.26
    颡
    0.26
    AndView
    0.25
    çĤ¹åįĬ
    0.24
     absent
    0.24
     alike
    0.24
    efd
    0.23
    phans
    0.23
    Activations Density 0.001%

    No Known Activations