© 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. 63723
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    ást
    -0.31
    çĥ¦
    -0.27
    ä¾Ŀ次
    -0.27
    .offsetWidth
    -0.25
    们
    -0.24
    á»Ĺi
    -0.24
    å¯ĦãģĽ
    -0.24
    otel
    -0.24
    ãģłãģij
    -0.24
    æĬ¥ä¸ļ
    -0.23
    POSITIVE LOGITS
     anything
    0.31
    åķľ
    0.30
     Any
    0.29
    anything
    0.29
    .decorators
    0.28
    ä»»ä½ķæŶåĢĻ
    0.27
    åħ±äº§åħļåijĺ
    0.26
     anyone
    0.26
    åIJİæľŁ
    0.26
    ä»»ä½ķ
    0.26
    Activations Density 6.345%

    No Known Activations