© 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. 19-TRANSCODER-HP
    7. 9298
    Prev
    Next
    INDEX
    Explanations

    Ordinal suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»¿åľ°
    -0.27
    ä¸įç»ı
    -0.24
    ä¸Ģçľ¼
    -0.23
    大è¡Ĺ
    -0.23
     exclude
    -0.23
     Gle
    -0.23
     Greenwich
    -0.23
    ç¾İ人
    -0.23
     malign
    -0.22
     pack
    -0.22
    POSITIVE LOGITS
    ductory
    0.28
    .–
    0.26
    å¾Ģè¿Ķ
    0.25
    vation
    0.25
    cheng
    0.25
     vic
    0.24
    trand
    0.24
    æŶéĹ´åĨħ
    0.24
    ditor
    0.23
    æ½ľåĬĽ
    0.23
    Activations Density 0.023%

    No Known Activations