© 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. 39876
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ymes
    -0.31
    ogy
    -0.28
     valid
    -0.28
     Big
    -0.28
     spot
    -0.27
    Spot
    -0.27
    èĮħ
    -0.27
    éra
    -0.26
    oks
    -0.26
     suppression
    -0.25
    POSITIVE LOGITS
    让æĤ¨
    0.28
    çīĪæĿĥ声æĺİ
    0.26
    Towards
    0.25
    ľ
    0.25
    åĿĬ
    0.25
    anian
    0.24
    veillance
    0.24
    oward
    0.24
    owards
    0.24
     artisan
    0.24
    Activations Density 0.877%

    No Known Activations