© 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. 40680
    Prev
    Next
    INDEX
    Explanations

    computers

    np_max-act · gemini-2.0-flash
    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
    æ©Ħæ¦Ħ
    -0.28
     consul
    -0.25
     exem
    -0.24
    éķ¿æķĪ
    -0.24
    衲
    -0.24
    ạt
    -0.24
    athe
    -0.24
    ear
    -0.24
    åĻ¤
    -0.24
     Impl
    -0.24
    POSITIVE LOGITS
     sandwiches
    0.27
    storybook
    0.25
    èµĦæľ¬
    0.25
    循
    0.25
    æľĢ大
    0.24
     pack
    0.24
    讨
    0.24
    ä½Ļé¢Ŀ
    0.24
    PTH
    0.24
    çŃ¹çłģ
    0.24
    Activations Density 0.217%

    No Known Activations