© 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. 40982
    Prev
    Next
    INDEX
    Explanations

    Battles and war

    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
     wor
    -0.30
    allel
    -0.28
    éĵ¾
    -0.28
    éĵ¾æĿ¡
    -0.26
    /Peak
    -0.25
    ä¸ĭä¸Ģ个
    -0.24
     Westminster
    -0.24
    éıĪ
    -0.24
    ABCDEFG
    -0.24
     chain
    -0.24
    POSITIVE LOGITS
     Trom
    0.26
    trasound
    0.26
    TURE
    0.26
    PJ
    0.24
    olated
    0.24
    æĿ¼
    0.24
     postfix
    0.24
     Stand
    0.24
    ä¿IJ
    0.24
     intended
    0.24
    Activations Density 0.093%

    No Known Activations