© 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. 40719
    Prev
    Next
    INDEX
    Explanations

    Code or mixed text

    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
    çİĭåĽ½
    -0.26
    èģ¯çµ¡
    -0.25
     exhibits
    -0.25
    rossover
    -0.24
     backed
    -0.24
    erah
    -0.24
    cta
    -0.24
     hoses
    -0.24
     crossover
    -0.24
    handleRequest
    -0.24
    POSITIVE LOGITS
     Medi
    0.27
    è²»
    0.27
    #error
    0.26
    éĤ£ä¹Īå¤ļ
    0.26
     Pública
    0.25
    令çīĮ
    0.25
    Ñĩик
    0.25
     complication
    0.25
    vi
    0.25
    éré
    0.24
    Activations Density 0.381%

    No Known Activations