© 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. 17990
    Prev
    Next
    INDEX
    Explanations

    scientific/medical papers

    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
    æŁ¥éªĮ
    -0.29
    ICI
    -0.28
    еÑĩен
    -0.28
    éĬĢ
    -0.27
     labs
    -0.27
     nomination
    -0.26
    æħ·æħ¨
    -0.26
    undy
    -0.26
    _gray
    -0.25
    riot
    -0.25
    POSITIVE LOGITS
    amel
    0.30
    ä¸įçĦ¶
    0.28
    磫
    0.26
    åIJ¦åĪĻ
    0.26
    æ±īåŃĹ
    0.25
    èĮĨ
    0.25
    AdapterManager
    0.25
    æľĽ
    0.25
     otherwise
    0.24
    ziehung
    0.24
    Activations Density 0.103%

    No Known Activations