© 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. 113045
    Prev
    Next
    INDEX
    Explanations

    treat

    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
    mia
    -0.29
    æ¯
    -0.28
     son
    -0.27
    irie
    -0.26
    .son
    -0.25
    jur
    -0.25
     Son
    -0.25
     jur
    -0.25
     mild
    -0.25
    çĥ«
    -0.25
    POSITIVE LOGITS
    ="?
    0.26
    Comple
    0.24
    arker
    0.24
    umer
    0.24
    baum
    0.24
    liner
    0.24
    atis
    0.24
     claimed
    0.24
    htable
    0.23
    ooled
    0.23
    Activations Density 0.013%

    No Known Activations