© 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. 27-TRANSCODER-HP
    7. 8790
    Prev
    Next
    INDEX
    Explanations

    Cleanliness/sterilization industrial/medical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iens
    -0.27
     e
    -0.26
    éĤ¸
    -0.25
     tele
    -0.25
     multif
    -0.25
    .kernel
    -0.25
     sun
    -0.25
     architects
    -0.24
     post
    -0.24
    .e
    -0.24
    POSITIVE LOGITS
    æ¸ħæ´ģ
    0.30
    æ´ģ
    0.28
    itary
    0.28
    é¾Ħ
    0.28
     cleansing
    0.27
    flush
    0.26
    好人
    0.26
    à¸Ĺำà¸Ħวามสะà¸Ńาà¸Ķ
    0.25
    éĻIJ度
    0.25
    AGED
    0.25
    Activations Density 0.001%

    No Known Activations