© 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. 25-TRANSCODER-HP
    7. 108016
    Prev
    Next
    INDEX
    Explanations

    medical imaging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inton
    -0.27
     feliz
    -0.25
     Supply
    -0.25
    supply
    -0.25
    Supply
    -0.25
     Behind
    -0.25
    æĮ½
    -0.25
     Funding
    -0.24
     Attach
    -0.24
    tein
    -0.24
    POSITIVE LOGITS
    çī¹çĤ¹
    0.26
    .charCodeAt
    0.26
    edly
    0.25
    çī¹å¾ģ
    0.25
     features
    0.25
    atsby
    0.25
     characteristics
    0.25
    activity
    0.24
    aturday
    0.24
     dry
    0.24
    Activations Density 1.059%

    No Known Activations