© 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. 40039
    Prev
    Next
    INDEX
    Explanations

    Business/Organizations

    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
     tweeting
    -0.27
     requested
    -0.27
    TEMP
    -0.26
    ÑĮе
    -0.25
    æĸĭ
    -0.25
     mandated
    -0.25
    charm
    -0.25
    .ylabel
    -0.24
     tweeted
    -0.24
    isode
    -0.24
    POSITIVE LOGITS
    éĿ
    0.28
    instead
    0.27
    éĩijåĪļ
    0.26
    åħ±äº§åħļåijĺ
    0.26
     instead
    0.26
    Instead
    0.25
    æľº
    0.25
    eries
    0.24
    å¸IJ篷
    0.24
     Instead
    0.24
    Activations Density 0.057%

    No Known Activations