© 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. 20-TRANSCODER-HP
    7. 141628
    Prev
    Next
    INDEX
    Explanations

    War and military operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æķ´
    -0.34
    å¤ļå¹´
    -0.29
    ve
    -0.28
    大è§Ħ模
    -0.27
    级
    -0.27
    åĮĸ
    -0.27
    积累
    -0.26
    è¿ĻæĿ¡
    -0.26
    ç©¿ä¸Ĭ
    -0.26
    ä¸ĢæĿ¡
    -0.26
    POSITIVE LOGITS
    Tween
    0.27
    indsight
    0.26
    anol
    0.26
    /component
    0.26
    æ°ĺ
    0.25
    Component
    0.25
    (SYS
    0.25
    å¯Ħæīĺ
    0.25
    -component
    0.24
    Injector
    0.24
    Activations Density 14.158%

    No Known Activations