© 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. 22-TRANSCODER-HP
    7. 129716
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tire
    -0.26
    otive
    -0.26
     confirmed
    -0.24
     son
    -0.23
    hazi
    -0.23
    åĵ¼
    -0.23
    .cloudflare
    -0.22
    DataExchange
    -0.22
    ¡°
    -0.22
    æĬĺ
    -0.22
    POSITIVE LOGITS
    BSD
    0.30
     detriment
    0.27
    æł¹æľ¬
    0.24
    æľ¬è´¨
    0.24
    icut
    0.24
    âĪ
    0.24
    Bearer
    0.23
    åĪĻ
    0.23
     negatives
    0.23
    ÑĥÑĤÑĮ
    0.23
    Activations Density 5.494%

    No Known Activations

    This feature has no known activations.