© 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. 19-TRANSCODER-HP
    7. 7705
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emat
    -0.27
    éĻ¤
    -0.26
    ughter
    -0.24
    cq
    -0.24
    太快
    -0.24
    æĸ°é¢ĸ
    -0.23
    åı¸ä»¤
    -0.23
     Ames
    -0.23
    deer
    -0.23
    çł´äº§
    -0.23
    POSITIVE LOGITS
    icle
    0.29
     steep
    0.26
    rolled
    0.26
    ç»ĻåŃ©åŃIJ
    0.26
     ad
    0.26
    arend
    0.26
     hyper
    0.24
    otal
    0.24
     cr
    0.24
    razil
    0.23
    Activations Density 0.848%

    No Known Activations

    This feature has no known activations.