© 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. 107173
    Prev
    Next
    INDEX
    Explanations

    the

    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
    erase
    -0.30
    éĿ¢åIJij
    -0.29
    æ±
    -0.29
    args
    -0.27
    æİ¢
    -0.26
    Dry
    -0.26
    AB
    -0.26
    ç½®
    -0.25
    å½¢
    -0.25
     per
    -0.25
    POSITIVE LOGITS
    getDb
    0.25
     Lights
    0.24
     besides
    0.24
    IColor
    0.23
     bure
    0.23
     undisclosed
    0.23
    usercontent
    0.23
    esian
    0.23
    (IServiceCollection
    0.23
    åıŁ
    0.23
    Activations Density 12.014%

    No Known Activations