© 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. 129661
    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
    estone
    -0.26
    éªĮ
    -0.26
    -decoration
    -0.25
     borderBottom
    -0.25
     ste
    -0.24
    olum
    -0.24
    ülü
    -0.24
    :]↵
    -0.24
    æ·Ģ
    -0.24
     ÑĤам
    -0.23
    POSITIVE LOGITS
    æĺ¼
    0.27
     park
    0.26
    uids
    0.26
    秩
    0.26
     upright
    0.26
    åı¦ä¸ĢåįĬ
    0.26
    =%.
    0.25
     Park
    0.25
    =".
    0.24
    prung
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.