© 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. 12-TRANSCODER-HP
    7. 22007
    Prev
    Next
    INDEX
    Explanations

    Formal documents and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ller
    -0.27
    aud
    -0.26
    uktur
    -0.26
    gere
    -0.26
    ato
    -0.25
    丰满
    -0.25
    arme
    -0.25
    arm
    -0.24
     kolej
    -0.24
    ax
    -0.24
    POSITIVE LOGITS
    åº
    0.29
    ÐIJÐŀ
    0.28
    ublisher
    0.27
    æīĩ
    0.27
    heten
    0.25
    isdiction
    0.25
    EFAULT
    0.25
    -haspopup
    0.24
    .gc
    0.24
     Ballard
    0.24
    Activations Density 0.008%

    No Known Activations