© 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. 108390
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åıĺå½¢
    -0.26
    ients
    -0.26
     discriminator
    -0.26
     HuffPost
    -0.25
     optarg
    -0.25
    ibern
    -0.25
     Elements
    -0.25
    æĦıè¯Ĩ
    -0.25
    _intent
    -0.25
     <![
    -0.25
    POSITIVE LOGITS
    %/
    0.26
    IME
    0.25
     pot
    0.23
     exp
    0.23
    éĵ¨
    0.23
     divisible
    0.23
    åµĮ
    0.23
    ))+
    0.23
    struction
    0.23
     divides
    0.23
    Activations Density 0.035%

    No Known Activations

    This feature has no known activations.