© 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. 12-TRANSCODER-HP
    7. 22670
    Prev
    Next
    INDEX
    Explanations

    Medical conditions/gland related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    letter
    -0.29
    precision
    -0.28
     Letters
    -0.27
     Letter
    -0.27
     letter
    -0.27
    è¶Ķ
    -0.26
    å°±åľ¨
    -0.25
    nap
    -0.25
    åĪĩåħ¥
    -0.25
    åĪ»æĦı
    -0.25
    POSITIVE LOGITS
     onCreate
    0.26
    instein
    0.26
    ifax
    0.26
     wh
    0.26
    åĢį
    0.25
    ivi
    0.25
    liches
    0.24
    à¸Ńาà¸ģาศ
    0.24
    alent
    0.24
    ovo
    0.24
    Activations Density 0.001%

    No Known Activations