© 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. 33-TRANSCODER-HP
    7. 54028
    Prev
    Next
    INDEX
    Explanations

    Food and ingredients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     component
    -0.46
    Component
    -0.46
     Component
    -0.45
     componente
    -0.42
    	component
    -0.42
    ç»Ħ件
    -0.41
     components
    -0.40
     Components
    -0.40
    component
    -0.40
    (Component
    -0.40
    POSITIVE LOGITS
    çŃ·
    0.32
    ingle
    0.25
    干活
    0.25
    责任åĪ¶
    0.25
    ifix
    0.24
    åı£æľį
    0.24
    ä¸ĢåŃĹ
    0.24
    éĵ±
    0.24
    æĮ¹
    0.24
     ims
    0.24
    Activations Density 0.011%

    No Known Activations