© 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. 86779
    Prev
    Next
    INDEX
    Explanations

    Computer 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
    åºĶ该
    -0.60
     should
    -0.60
    åºĶ该æĺ¯
    -0.57
     shouldn
    -0.56
     supposed
    -0.54
    åºĶæľīçļĦ
    -0.53
    should
    -0.53
    ä¸įåºĶ该
    -0.52
     Should
    -0.51
    Should
    -0.50
    POSITIVE LOGITS
     admir
    0.28
    amin
    0.27
    åħľ
    0.27
    issen
    0.25
    .mods
    0.25
    ĵįä½ľ
    0.24
    boards
    0.24
    éĥ¯
    0.24
     bleach
    0.24
    ä½łåĸľæ¬¢
    0.24
    Activations Density 0.001%

    No Known Activations