© 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. 40706
    Prev
    Next
    INDEX
    Explanations

    Aviation/Flight

    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
     ngo
    -0.28
     crack
    -0.27
     al
    -0.26
    amer
    -0.25
     ACK
    -0.25
    æŀģ
    -0.25
    MAL
    -0.25
    wh
    -0.25
    ack
    -0.25
     reflected
    -0.25
    POSITIVE LOGITS
    creens
    0.27
    è¿ĺä¸įæĺ¯
    0.26
    asan
    0.26
    ombine
    0.26
    isure
    0.26
    æīĭæĦŁ
    0.26
    çµĤæĸ¼
    0.25
    ä¾¿å®ľ
    0.25
    ¢åįķ
    0.25
    ustin
    0.25
    Activations Density 0.094%

    No Known Activations