© 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. 86849
    Prev
    Next
    INDEX
    Explanations

    Exclamations and questions

    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
    cul
    -0.30
    ...]↵↵
    -0.29
    太太
    -0.28
    ugh
    -0.25
    culator
    -0.24
    OLID
    -0.24
    otec
    -0.23
    ensions
    -0.23
     relic
    -0.23
    RARY
    -0.23
    POSITIVE LOGITS
     Other
    0.26
     Unt
    0.25
    sound
    0.25
    èĢĮåĩº
    0.25
    åħ¶ä»ĸ
    0.25
      ↵
    0.25
    pon
    0.25
     As
    0.24
    èĮļ
    0.23
    иÑİ
    0.23
    Activations Density 0.046%

    No Known Activations