© 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. 40618
    Prev
    Next
    INDEX
    Explanations

    Code and technical language

    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
    Ca
    -0.26
    æī§è¡ĮåĬĽ
    -0.25
    terr
    -0.24
    åĨ³å¿ĥ
    -0.24
    çļĦ妻åŃIJ
    -0.24
    ä¸Ģä½ĵåĮĸ
    -0.23
    leneck
    -0.23
    loo
    -0.23
    çļĦ第ä¸Ģ个
    -0.23
     Ca
    -0.23
    POSITIVE LOGITS
    èµ·æºIJ
    0.28
     branches
    0.27
    ·»
    0.27
    FIELDS
    0.26
     Sweat
    0.26
     origin
    0.25
     Ole
    0.25
    ãģĬãģĭ
    0.25
     Ever
    0.25
    away
    0.25
    Activations Density 0.649%

    No Known Activations