© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41641
    Prev
    Next
    INDEX
    Explanations

    Scientific descriptions

    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
    Negative Logits
    asion
    -0.30
     op
    -0.26
    åİĨ
    -0.26
    èģĶ社
    -0.26
    èĩª
    -0.26
    ologies
    -0.25
    æľīè¿ĩ
    -0.25
    ilon
    -0.24
    è¯Ŀ
    -0.24
    群
    -0.24
    POSITIVE LOGITS
    =~
    0.28
    桧
    0.28
    usher
    0.27
    ä¸īå±Ĥ
    0.27
    ä¸ī代
    0.26
     Dish
    0.25
    ä¼ļå½±åĵįåĪ°
    0.25
    ä¸īçĤ¹
    0.25
    DDD
    0.24
    !↵↵↵↵
    0.24
    Activations Density 1.801%

    No Known Activations