© 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. 27-TRANSCODER-HP
    7. 9923
    Prev
    Next
    INDEX
    Explanations

    foreign or gibberish

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .sessions
    -0.29
    sessionId
    -0.29
     auss
    -0.28
     Real
    -0.27
    æģļ
    -0.26
     asymmetric
    -0.26
    éĩijåŃĹ
    -0.25
    ramid
    -0.25
    åıijå±ķæľºéģĩ
    -0.25
    onis
    -0.25
    POSITIVE LOGITS
    SOR
    0.27
     Zot
    0.27
    etter
    0.25
    å¢ĥçķĮ
    0.25
    recated
    0.24
    ä¼ĺ
    0.24
    iferay
    0.24
     Grat
    0.23
    港
    0.23
    å¿ĥæĥħ
    0.23
    Activations Density 0.002%

    No Known Activations