© 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. 39845
    Prev
    Next
    INDEX
    Explanations

    at

    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
    igli
    -0.27
    íĶĮ
    -0.26
    createForm
    -0.26
    анÑģ
    -0.25
     âĩ
    -0.25
    .addHandler
    -0.25
    âĩ§
    -0.24
    rowning
    -0.24
    å¾Īæ·±
    -0.24
    çłº
    -0.24
    POSITIVE LOGITS
    etat
    0.28
    åģľ
    0.27
    ito
    0.27
    æĹĹ
    0.26
    wg
    0.26
    -framework
    0.25
    æĭ¨
    0.25
    两个æľĪ
    0.24
    eea
    0.24
    åīįåIJİ
    0.23
    Activations Density 1.401%

    No Known Activations