© 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. 31-TRANSCODER-HP
    7. 19692
    Prev
    Next
    INDEX
    Explanations

    Programming and technical topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æĺ¯ä¸ĢåĢĭ
    -0.48
    æĺ¯ä¸Ģ个
    -0.48
    æĺ¯ä¸ª
    -0.45
    è¿Ļæĺ¯ä¸Ģ个
    -0.44
    æĺ¯ä¸Ģ
    -0.41
    å°±æĺ¯ä¸Ģ个
    -0.36
    æĺ¯ä¸Ģéĥ¨
    -0.35
    æĺ¯ä¸Ģ座
    -0.34
    —a
    -0.33
    æĺ¯ä¸Ģä½į
    -0.32
    POSITIVE LOGITS
    åı¦ä¸Ģæĸ¹éĿ¢
    0.32
     Age
    0.29
     age
    0.26
    hi
    0.25
    A
    0.25
    åı¦ä¸Ģç§į
    0.25
    åı¦
    0.24
    åıĪ被
    0.24
    ack
    0.24
    леÑĤ
    0.23
    Activations Density 7.971%

    No Known Activations