© 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. 129960
    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
    Ã¼ÃŁ
    -0.28
     orient
    -0.26
     insert
    -0.24
     actions
    -0.24
     shoot
    -0.24
     exterior
    -0.24
    æ©Ļ
    -0.24
     sharp
    -0.23
    inside
    -0.23
     directed
    -0.23
    POSITIVE LOGITS
    bilit
    0.27
    itic
    0.25
    olin
    0.25
    买车
    0.25
    .charAt
    0.24
    ephy
    0.24
    ä¸Ģèµ·
    0.24
    &s
    0.23
    inburgh
    0.23
    ä¸Ģ缴æĺ¯
    0.23
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.