© 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. 40141
    Prev
    Next
    INDEX
    Explanations

    Greek/Roman classicism

    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
     paper
    -0.30
    ç¬ĥ
    -0.29
    pher
    -0.28
    íĶ¼
    -0.26
     pare
    -0.25
    ä¸įåıĹ
    -0.25
     manuscript
    -0.25
     tones
    -0.24
     Script
    -0.24
    SCRIPT
    -0.24
    POSITIVE LOGITS
    rete
    0.29
    atables
    0.27
    utow
    0.27
    apus
    0.25
    è¿Ļæł·ä¸Ģ
    0.25
    ооÑĢÑĥж
    0.24
     Remix
    0.24
    æij©
    0.24
    åĴĮå°ļ
    0.24
    èĮ¬
    0.24
    Activations Density 0.144%

    No Known Activations