© 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. 40266
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
     among
    -0.29
    als
    -0.26
     drained
    -0.25
    art
    -0.25
     processed
    -0.24
    åĬ¨
    -0.24
     primarily
    -0.24
    athers
    -0.23
    Among
    -0.23
    [][]
    -0.23
    POSITIVE LOGITS
     Place
    0.29
    æĪijçĽ¸ä¿¡
    0.28
     Places
    0.27
    ifest
    0.27
    /place
    0.27
     autoload
    0.26
    APTER
    0.25
    ãĥĶãĥ³
    0.25
    æĸ°éĹ»ç½ij
    0.25
    è¿Ļå¥Ĺ
    0.25
    Activations Density 0.733%

    No Known Activations