© 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. 31-TRANSCODER-HP
    7. 18397
    Prev
    Next
    INDEX
    Explanations

    Food containers/packaging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æľºåĬ¨
    -0.28
    ite
    -0.26
    oard
    -0.25
    èµĦæºIJ
    -0.25
    hoa
    -0.25
    cir
    -0.25
     converse
    -0.25
    æ³ķåºŃ
    -0.24
     ev
    -0.24
    	ev
    -0.24
    POSITIVE LOGITS
     tub
    0.28
     ÑĢаÑģпÑĢоÑģÑĤÑĢан
    0.28
     Packs
    0.28
    åĮħè£ħ
    0.28
     packs
    0.27
    é¦ĭ
    0.27
     containers
    0.26
     packing
    0.26
     packaging
    0.26
     Pack
    0.26
    Activations Density 0.344%

    No Known Activations