© 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. 27-TRANSCODER-HP
    7. 9057
    Prev
    Next
    INDEX
    Explanations

    digging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mounts
    -0.29
     mount
    -0.29
     поÑģл
    -0.28
    æİ¥å¾ħ
    -0.28
    å¸ĸ
    -0.27
     Mount
    -0.26
     signed
    -0.26
    esco
    -0.26
    uno
    -0.25
    æĭĵ
    -0.25
    POSITIVE LOGITS
    åľ°ä¸ĭ
    0.34
     excavation
    0.32
     underground
    0.32
    åľ°ä¸Ń
    0.32
    æĮĸ
    0.32
     digging
    0.31
    åľ°
    0.31
     dug
    0.31
     buried
    0.30
     excav
    0.30
    Activations Density 0.007%

    No Known Activations