© 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. 40299
    Prev
    Next
    INDEX
    Explanations

    Various text sources/snippets

    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
    å¾Ļ
    -0.28
    uctions
    -0.26
    alie
    -0.26
    so
    -0.25
    udson
    -0.25
    åıªåī©
    -0.25
    ä¸Ģåı£
    -0.25
    estation
    -0.25
    gie
    -0.25
    PN
    -0.24
    POSITIVE LOGITS
    æĶ¥
    0.29
    orde
    0.28
     addUser
    0.27
     robes
    0.25
    主ä¹īèĢħ
    0.24
    ︰
    0.23
    çļĦæľºä¼ļ
    0.23
    BCM
    0.23
    /icons
    0.23
    ç¨ĥ
    0.23
    Activations Density 0.102%

    No Known Activations