© 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. 110935
    Prev
    Next
    INDEX
    Explanations

    Mixture of different content

    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
    romise
    -0.32
    æĪŁ
    -0.28
    avery
    -0.26
    å°ij
    -0.25
    IZE
    -0.25
     Bros
    -0.25
    IFE
    -0.24
    tha
    -0.24
     expected
    -0.24
    icularly
    -0.23
    POSITIVE LOGITS
     trần
    0.27
    çĮ·
    0.25
    loff
    0.25
    ç¢İçīĩ
    0.25
    åĬ¨çĶŁæĪIJ
    0.25
     matters
    0.24
    å¾Ĺèµ·
    0.24
     lives
    0.24
    è·¯è¿ĩ
    0.24
     autogenerated
    0.24
    Activations Density 0.003%

    No Known Activations