© 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. 58289
    Prev
    Next
    INDEX
    Explanations

    technical/complex content

    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
    Not in Any Lists

    No Comments

    Negative Logits
    eways
    -0.30
     convo
    -0.28
     additive
    -0.27
    æĹłåı¯
    -0.27
    .Callback
    -0.26
    iras
    -0.26
    xef
    -0.26
     recalls
    -0.25
    enumerator
    -0.25
     touches
    -0.24
    POSITIVE LOGITS
    åIJ¸å¼ķäºĨ
    0.31
    issance
    0.30
    èĮĮ
    0.28
    æµģåĬ¨
    0.26
    æľĢéļ¾
    0.26
     -↵
    0.26
    ainers
    0.26
    åIJ¸å¼ķåĬĽ
    0.26
     poder
    0.25
    istung
    0.25
    Activations Density 0.001%

    No Known Activations