© 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. 40488
    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
     Commons
    -0.28
     Libraries
    -0.26
    çļĦ身份
    -0.25
    ertools
    -0.24
    åºĵ
    -0.24
    elas
    -0.24
    inged
    -0.24
    esting
    -0.24
    away
    -0.24
     gens
    -0.24
    POSITIVE LOGITS
    纶
    0.28
    宽
    0.26
     fa
    0.25
     operative
    0.25
    缴
    0.24
     piv
    0.24
    æī®æ¼Ķ
    0.24
     suce
    0.24
    éĥ½è¯´
    0.24
    触
    0.23
    Activations Density 0.060%

    No Known Activations

    This feature has no known activations.