© 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. 39950
    Prev
    Next
    INDEX
    Explanations

    Code and names

    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
    icles
    -0.28
    ä¼ı
    -0.27
    æłĩå¿Ĺ
    -0.27
    лов
    -0.26
    ç²¾
    -0.25
    满æĦı
    -0.25
    å£ģåŀĴ
    -0.25
    w
    -0.25
    CSS
    -0.24
    纸
    -0.24
    POSITIVE LOGITS
    alte
    0.34
    usting
    0.28
     Canter
    0.26
    jong
    0.25
    __),
    0.25
    inflate
    0.25
    é¾Ľ
    0.25
    ãģĦãģŁãģłãģį
    0.25
    .Abstract
    0.25
     Nz
    0.24
    Activations Density 0.039%

    No Known Activations