© 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. 30-TRANSCODER-HP
    7. 96433
    Prev
    Next
    INDEX
    Explanations

    breast cancer, medical procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ently
    -0.28
    辦
    -0.26
    çĭĻåĩ»
    -0.25
    åģ¾
    -0.25
    itious
    -0.25
     recurrent
    -0.25
    /rec
    -0.25
     Rec
    -0.25
     dipping
    -0.24
    溺
    -0.24
    POSITIVE LOGITS
    Instagram
    0.30
    uyo
    0.29
    estr
    0.28
    éĽª
    0.26
     jam
    0.26
    estro
    0.26
    ongo
    0.25
     comp
    0.25
    èĦ¸
    0.24
     orbit
    0.24
    Activations Density 0.123%

    No Known Activations