© 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. 129851
    Prev
    Next
    INDEX
    Explanations

    general text passages

    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
    ä¸Ģ身
    -0.28
    yes
    -0.27
    æīįç®Ĺ
    -0.27
    æݪ
    -0.27
    表彰
    -0.26
    YES
    -0.26
    deny
    -0.25
    æīĢè¬Ĥ
    -0.25
    flu
    -0.25
    欢åij¼
    -0.25
    POSITIVE LOGITS
    {}\
    0.25
     Scratch
    0.24
    enic
    0.24
    çİ°
    0.24
    fic
    0.24
    ervice
    0.23
    offs
    0.23
    ([{
    0.23
    æŀĦéĢł
    0.23
     Slice
    0.23
    Activations Density 12.972%

    No Known Activations