© 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. 20-TRANSCODER-HP
    7. 63587
    Prev
    Next
    INDEX
    Explanations

    drugs, medical treatments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¿ĹæĦ¿
    -0.29
     RECEIVE
    -0.27
    äºĭ迹
    -0.25
    表çĻ½
    -0.25
     regret
    -0.24
    egl
    -0.24
     Receive
    -0.24
    pare
    -0.24
     Slots
    -0.23
     VOL
    -0.23
    POSITIVE LOGITS
    usto
    0.28
    anal
    0.28
    åħ«åŃĹ
    0.27
     packs
    0.27
    ena
    0.27
    elastic
    0.27
    owitz
    0.27
     CommonModule
    0.26
     barrel
    0.25
    ried
    0.24
    Activations Density 10.686%

    No Known Activations