© 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. 130416
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    社
    -0.28
     assoc
    -0.28
    åı²
    -0.26
    VILLE
    -0.26
     Assoc
    -0.25
     histories
    -0.25
     association
    -0.25
    èĭŀ
    -0.25
    amat
    -0.25
    æīĵåħ¥
    -0.25
    POSITIVE LOGITS
    KIT
    0.26
    éĺ²æŃ¢
    0.26
     spared
    0.26
    âĩ¥
    0.26
    ä¸Ģè§Ī
    0.25
    åīįæīĢ
    0.25
    æ°´æºIJ
    0.25
    éĺ²èĮĥ
    0.24
     Listing
    0.24
    InThe
    0.24
    Activations Density 33.810%

    No Known Activations