© 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. 112741
    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
    elize
    -0.27
     senate
    -0.26
     trance
    -0.24
     German
    -0.23
    atives
    -0.23
    sı
    -0.23
    ycler
    -0.23
    jets
    -0.23
    óż
    -0.23
    ç¼Ĵ
    -0.23
    POSITIVE LOGITS
    å¥Ī
    0.31
    ä¿¡
    0.30
    带
    0.28
    æĸ¹éĿ¢çļĦ
    0.28
    é£İ
    0.27
    åIJį
    0.27
    çħ§
    0.27
    çĿĢåĬĽ
    0.27
    çĹħæ¯Ĵ
    0.27
    åĬ³
    0.26
    Activations Density 0.014%

    No Known Activations

    This feature has no known activations.