© 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. 88774
    Prev
    Next
    INDEX
    Explanations

    reference markers

    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
    åİ»äºĨ
    -0.26
    aspect
    -0.25
    è¿Ĥ
    -0.25
    ('@
    -0.25
    æ°´åŁŁ
    -0.25
     cru
    -0.24
    aron
    -0.24
    -around
    -0.24
     aspect
    -0.23
     æĺ
    -0.23
    POSITIVE LOGITS
     illeg
    0.26
    avig
    0.26
    ä¸¥æł¼çļĦ
    0.25
    .TypeOf
    0.25
    agy
    0.25
    Fat
    0.25
    åŁ´
    0.25
    èIJ©
    0.24
    MethodName
    0.24
     NSIndexPath
    0.24
    Activations Density 1.219%

    No Known Activations