© 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. 40238
    Prev
    Next
    INDEX
    Explanations

    living

    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
    reste
    -0.29
    wich
    -0.28
    orum
    -0.28
    MISSION
    -0.27
    à¹ģà¸Ķà¸ĩ
    -0.26
    addOn
    -0.26
    ipp
    -0.26
    elli
    -0.24
    ompiler
    -0.24
    glas
    -0.24
    POSITIVE LOGITS
    ufe
    0.28
     men
    0.26
     LV
    0.26
    atu
    0.26
    æīĢè°ĵçļĦ
    0.25
     NB
    0.25
     fc
    0.24
    iot
    0.23
     fee
    0.23
    Next
    0.23
    Activations Density 1.814%

    No Known Activations