© 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. 18-TRANSCODER-HP
    7. 89697
    Prev
    Next
    INDEX
    Explanations

    retain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ampire
    -0.27
    åĵ¡
    -0.24
    Sou
    -0.24
    nets
    -0.24
    ath
    -0.24
     commute
    -0.23
    nor
    -0.23
    åı¹
    -0.23
     Mirror
    -0.23
    presso
    -0.23
    POSITIVE LOGITS
    æĭ¨
    0.27
    uce
    0.25
    omics
    0.24
    æݨ
    0.24
    æĹłçĸij
    0.23
    èĬ
    0.23
    ophys
    0.23
     assemblies
    0.23
    æĭĶ
    0.23
    jamin
    0.23
    Activations Density 28.819%

    No Known Activations