© 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. 40172
    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
    iy
    -0.26
    iei
    -0.25
    çļĦä¹łæĥ¯
    -0.24
    ipl
    -0.24
     proof
    -0.24
    äºĶè¡Į
    -0.24
    (rad
    -0.23
    -columns
    -0.23
    ãĢij,ãĢIJ
    -0.23
    çļĦå½±åĵį
    -0.22
    POSITIVE LOGITS
    edy
    0.32
    tur
    0.27
    ught
    0.27
    Äı
    0.26
    ariant
    0.26
    ieri
    0.25
    åľ¨è¿Ļæĸ¹éĿ¢
    0.25
    ä¼ļéķ¿
    0.25
     Fraser
    0.25
    PRETTY
    0.24
    Activations Density 0.267%

    No Known Activations

    This feature has no known activations.