© 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. 130003
    Prev
    Next
    INDEX
    Explanations

    organizations, teams, centers, systems

    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
    amble
    -0.32
    ¦Ĥ
    -0.27
    åIJĮæĥħ
    -0.27
    emics
    -0.27
    御
    -0.26
    omens
    -0.26
    oling
    -0.25
    annabin
    -0.24
    æľĭåıĭåľĪ
    -0.24
    汨
    -0.24
    POSITIVE LOGITS
    akh
    0.26
    rez
    0.26
    念
    0.26
    éĢĤ度
    0.25
    legend
    0.25
    ä¼ĺ
    0.25
    å½¢
    0.24
     ISSN
    0.24
    ä¸İåħ¶
    0.24
    ι
    0.24
    Activations Density 5.255%

    No Known Activations