© 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. 14-TRANSCODER-HP
    7. 40241
    Prev
    Next
    INDEX
    Explanations

    medical terminology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĻ«
    -0.32
    ¢åįķ
    -0.31
    ä¸Ĭè°ĥ
    -0.28
    ouns
    -0.26
     //~
    -0.26
    æ°ĶåĢĻ
    -0.25
    nowled
    -0.25
    rets
    -0.25
    åħ¶å®ĥéĹ®é¢ĺ
    -0.24
    esh
    -0.23
    POSITIVE LOGITS
    chter
    0.28
    ikh
    0.28
    "):↵
    0.25
    åĮĸçļĦ
    0.25
    ']:↵
    0.25
    "]:↵
    0.24
    '):↵
    0.24
    举
    0.24
    ological
    0.23
    "):č↵
    0.23
    Activations Density 1.350%

    No Known Activations