© 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. 33-TRANSCODER-HP
    7. 54182
    Prev
    Next
    INDEX
    Explanations

    pain and medical studies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĽĺ
    -0.32
     Plate
    -0.29
    çĽĨ
    -0.29
    burg
    -0.27
    åŃIJ
    -0.27
    æĿ¿
    -0.26
    elib
    -0.25
    缤
    -0.25
    PB
    -0.25
    رÙĬÙĤ
    -0.25
    POSITIVE LOGITS
     oste
    0.27
     nerve
    0.25
    clamp
    0.25
     nor
    0.24
    spath
    0.24
    existent
    0.24
     widespread
    0.24
     procedure
    0.24
     hazard
    0.24
    sw
    0.24
    Activations Density 0.024%

    No Known Activations