© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 140932
    Prev
    Next
    INDEX
    Explanations

    and

    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
     coinc
    -0.27
    ematics
    -0.26
    ä¾ĭå¦Ĥ
    -0.25
    mund
    -0.25
    梵
    -0.25
    åıĤèĢĥèµĦæĸĻ
    -0.24
    oreach
    -0.24
    \b
    -0.24
    åij±
    -0.24
    atures
    -0.24
    POSITIVE LOGITS
    ãģ¨ãģĨ
    0.29
    ero
    0.26
    ihan
    0.25
    olson
    0.25
    ç½ijéĢļ
    0.24
     دÙĬ
    0.24
     Af
    0.23
    ache
    0.23
    ][-
    0.23
    abbo
    0.23
    Activations Density 20.141%

    No Known Activations