© 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. 41204
    Prev
    Next
    INDEX
    Explanations

    Cystic Fibrosis

    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
    å¨ĺ
    -0.28
    hi
    -0.28
     Stock
    -0.27
    èľ¥
    -0.24
     deprived
    -0.24
     cry
    -0.24
     Tavern
    -0.24
    ä¹ľ
    -0.24
    天æīį
    -0.24
    uitar
    -0.23
    POSITIVE LOGITS
    ism
    0.31
    rex
    0.29
     reminders
    0.28
     lå
    0.28
     reminder
    0.27
    FirstResponder
    0.26
    éĥ¨å§Ķ
    0.26
    ses
    0.26
     remind
    0.25
     há»Ļ
    0.25
    Activations Density 0.409%

    No Known Activations