© 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. 39940
    Prev
    Next
    INDEX
    Explanations

    Government, "ov", video software

    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
    awner
    -0.28
    ç´§åĩij
    -0.27
    ä¸įåĩºæĿ¥
    -0.27
    èĨı
    -0.25
    rx
    -0.25
     metav
    -0.25
    /method
    -0.25
    steller
    -0.24
     Morr
    -0.24
    -any
    -0.24
    POSITIVE LOGITS
    eres
    0.29
    es
    0.28
    qu
    0.26
    l
    0.26
    软
    0.25
    åĩij
    0.25
    ŀæĢ§
    0.24
    oscope
    0.24
     flavors
    0.24
    .ceil
    0.24
    Activations Density 0.482%

    No Known Activations