© 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. 107176
    Prev
    Next
    INDEX
    Explanations

    (

    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
    à¹Ĥม
    -0.29
    æij©
    -0.28
    æĪij们çļĦ
    -0.28
     ha
    -0.26
    è¿Ļä¹Ī说
    -0.26
    ascar
    -0.25
    æıIJ
    -0.25
    çĴĩ
    -0.24
     asserting
    -0.23
    å§ij
    -0.23
    POSITIVE LOGITS
     Legend
    0.28
    .run
    0.27
     couple
    0.26
    ="{!!
    0.26
     pair
    0.26
    ħ§
    0.26
     lighten
    0.25
     run
    0.25
     '*'
    0.25
    æĹ¥æľ¬äºº
    0.25
    Activations Density 12.416%

    No Known Activations