© 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. 56763
    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
    strument
    -0.27
    velt
    -0.25
    æħĭ
    -0.25
    åı¬åĽŀ
    -0.25
    xmlns
    -0.25
     commission
    -0.25
    Commission
    -0.24
     Krish
    -0.24
    æ±Łæ·®
    -0.23
     act
    -0.23
    POSITIVE LOGITS
    lef
    0.28
     Than
    0.27
    unge
    0.27
    è¿ĺä¸į
    0.25
     impression
    0.24
     Adler
    0.24
    imed
    0.24
    \/\/
    0.23
     Beitrag
    0.23
     أع
    0.23
    Activations Density 0.011%

    No Known Activations

    This feature has no known activations.