© 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. 27-TRANSCODER-HP
    7. 57563
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ËĬ
    -0.26
    iculty
    -0.25
     worthwhile
    -0.25
    ç¥
    -0.25
    ä¸ij
    -0.25
    è´µ
    -0.25
    æĹłæķĪ
    -0.24
    ahead
    -0.24
    æľīçĽĬ
    -0.24
    IJľ
    -0.24
    POSITIVE LOGITS
    Ger
    0.30
    INET
    0.26
     MES
    0.25
    大å¸Ī
    0.25
    respons
    0.25
    appers
    0.24
     filt
    0.24
    ovies
    0.24
     Ger
    0.24
    åĽºå®ļçļĦ
    0.24
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.