© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 31-TRANSCODER-HP
    7. 18614
    Prev
    Next
    INDEX
    Explanations

    scientific/medical/biological texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     shed
    -0.28
    çļĦéĤ£ç§į
    -0.27
    ìĪĺ
    -0.27
     sociology
    -0.26
    欧ç¾İ
    -0.25
    æĹħ游å±Ģ
    -0.25
    è§Ĵ度çľĭ
    -0.24
     politics
    -0.24
     Sociology
    -0.24
    å·¥åķĨå±Ģ
    -0.24
    POSITIVE LOGITS
     processes
    0.41
     player
    0.36
     players
    0.36
     cellular
    0.34
    process
    0.33
    Processes
    0.33
    player
    0.33
     Processes
    0.32
    -player
    0.32
    ä¸ĩæĪ·
    0.32
    Activations Density 1.727%

    No Known Activations