© 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. 14-TRANSCODER-HP
    7. 40021
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĢин
    -0.32
    [:]
    -0.28
    rowse
    -0.26
     CLR
    -0.25
    åı¦æľī
    -0.25
    idor
    -0.24
    çķ¸å½¢
    -0.24
     Rowe
    -0.24
    -ROM
    -0.24
    .ResponseWriter
    -0.23
    POSITIVE LOGITS
    ion
    0.30
    adesh
    0.27
    æĸĩä¸Ń
    0.25
    dy
    0.24
    èĬĭ
    0.24
    free
    0.24
    cation
    0.24
    çļĦæĸĩç«ł
    0.24
    èģĮä¸ļ
    0.23
    éĢĨè¢Ń
    0.23
    Activations Density 2.162%

    No Known Activations

    This feature has no known activations.