© 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. 140817
    Prev
    Next
    INDEX
    Explanations

    Maz

    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
    Negative Logits
    对ä¸įèµ·
    -0.25
    infra
    -0.25
     ITS
    -0.24
    gg
    -0.24
    SY
    -0.24
    itters
    -0.23
    deen
    -0.23
    rians
    -0.23
     Minister
    -0.23
    APT
    -0.23
    POSITIVE LOGITS
    ês
    0.30
     mẽ
    0.25
    BILE
    0.25
    å½ĵå±Ģ
    0.25
    æ¹ĸåĮº
    0.25
    ган
    0.25
    gli
    0.25
    æ³IJ
    0.24
     Fé
    0.24
    é¾Ħ
    0.24
    Activations Density 81.178%

    No Known Activations