© 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. 7665
    Prev
    Next
    INDEX
    Explanations

    Technical/formal writing snippets

    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
    åĪłéĻ¤
    -0.29
     Destruction
    -0.28
    æĬ¥åºŁ
    -0.28
    deleted
    -0.27
     deleted
    -0.27
    åĪłéĻ¤æĪIJåĬŁ
    -0.27
    缺失
    -0.26
     deletes
    -0.26
    evice
    -0.26
    indsight
    -0.25
    POSITIVE LOGITS
    åĮ»éĻ¢
    0.28
    çī©è´¨
    0.28
     hospital
    0.28
    amburger
    0.27
    оÑģÑĤоÑı
    0.25
    ç¿»
    0.25
     ÑģоÑģÑĤав
    0.25
    enger
    0.25
    è±ĨèħIJ
    0.24
    åĪ°åľº
    0.24
    Activations Density 0.000%

    No Known Activations