© 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. 20-TRANSCODER-HP
    7. 108169
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouve
    -0.29
    æĿŀ
    -0.29
    åĶ¯ä¸ĢçļĦ
    -0.28
    amac
    -0.27
    æĸ¡
    -0.26
    -sem
    -0.26
    åıªèĥ½
    -0.26
    yleft
    -0.25
     ONLY
    -0.25
     nonetheless
    -0.25
    POSITIVE LOGITS
    Among
    0.27
     Among
    0.25
    ner
    0.24
    _due
    0.24
    stem
    0.24
    æľīæľºä¼ļ
    0.24
    among
    0.24
    turned
    0.24
    bearing
    0.23
    æĮ
    0.23
    Activations Density 24.480%

    No Known Activations