© 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. 40159
    Prev
    Next
    INDEX
    Explanations

    Business/Corporate structure

    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
    ima
    -0.29
    iform
    -0.26
     lia
    -0.26
    å·¡åĽŀ
    -0.25
    ProcessEvent
    -0.25
    ison
    -0.25
    Circular
    -0.25
     Bryant
    -0.24
    .circular
    -0.24
     Mobil
    -0.24
    POSITIVE LOGITS
    proxy
    0.30
     prox
    0.30
     proxy
    0.28
    (proxy
    0.26
    åĮ¡
    0.26
    çī©æµģä¼ģä¸ļ
    0.26
    è¶Ĭ
    0.25
     chili
    0.25
    KG
    0.24
     Proxy
    0.24
    Activations Density 0.429%

    No Known Activations