© 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. 20-TRANSCODER-HP
    7. 130566
    Prev
    Next
    INDEX
    Explanations

    stadium

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    夷
    -0.28
    angan
    -0.27
    ä¸Ģæĸ¹éĿ¢
    -0.27
    æ°´çĶµ
    -0.27
     MyBase
    -0.26
    人为
    -0.26
    vore
    -0.25
    uku
    -0.25
    inke
    -0.25
    ãĢģ“
    -0.25
    POSITIVE LOGITS
     vinc
    0.28
    EMENT
    0.27
     cors
    0.26
     Concurrent
    0.26
    _aw
    0.24
    éĶ¢
    0.24
     moments
    0.24
     bull
    0.24
     camps
    0.23
    itter
    0.23
    Activations Density 1.878%

    No Known Activations