© 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. 18356
    Prev
    Next
    INDEX
    Explanations

    diseases and illnesses

    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
     conditions
    -1.50
     condition
    -1.49
    æĿ¡ä»¶
    -1.44
     Conditions
    -1.38
     Condition
    -1.33
    conditions
    -1.30
    condition
    -1.29
    Conditions
    -1.25
    Condition
    -1.24
    æ¢Ŀ件
    -1.18
    POSITIVE LOGITS
    å¾Ĺ
    0.27
     Advent
    0.26
    vern
    0.25
    uy
    0.24
    _again
    0.24
    å¾ĹäºĨ
    0.23
    çı©
    0.23
    oku
    0.23
    é¢į
    0.23
     accus
    0.23
    Activations Density 31.952%

    No Known Activations