© 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. 107951
    Prev
    Next
    INDEX
    Explanations

    legal documents, numbers, dates

    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
    \TestCase
    -0.24
    åİ¿å§Ķ书记
    -0.24
    è¿Ļéĥ¨åĪĨ
    -0.23
    åĽ½åĨħå¸Ĥåľº
    -0.23
    olecular
    -0.23
    Ỽt
    -0.23
     conting
    -0.23
    åį´æĺ¯
    -0.23
    ×Ļק
    -0.23
     prank
    -0.22
    POSITIVE LOGITS
    opers
    0.27
     Spl
    0.27
    acct
    0.27
    缮çĿ¹
    0.26
    Spl
    0.26
    缼å¼Ģ
    0.26
     gaping
    0.26
     versa
    0.26
    zy
    0.25
    éĽªèĬ±
    0.25
    Activations Density 1.819%

    No Known Activations