© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88252
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     constit
    -0.22
    <IM
    -0.22
    æĬ¥ç¤¾
    -0.21
     quar
    -0.21
     recon
    -0.21
    ÑĩеÑĢ
    -0.21
     deltas
    -0.20
    Frames
    -0.20
     dissoci
    -0.20
     frames
    -0.20
    POSITIVE LOGITS
    缸åIJĮçļĦ
    0.24
    else
    0.23
    åİ»çľĭçľĭ
    0.23
    è°Ĭ
    0.22
    æ°ijæĹıæĸĩåĮĸ
    0.22
    ä½łä¹Ł
    0.22
    æĮ¡ä½ı
    0.22
    å°¼äºļ
    0.22
    verse
    0.22
    ly
    0.22
    Activations Density 0.056%

    No Known Activations

    This feature has no known activations.