© 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. 63361
    Prev
    Next
    INDEX
    Explanations

    Technical snippets

    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
    æ¿Ģ
    -0.31
     altogether
    -0.28
    yes
    -0.26
    ayer
    -0.26
    ãģĿãĤĮãģ§ãĤĤ
    -0.25
     fmt
    -0.25
    UI
    -0.25
    娱ä¹IJåľº
    -0.24
     Interracial
    -0.24
    -layer
    -0.24
    POSITIVE LOGITS
    ifice
    0.26
    éĽĨè£ħ
    0.25
     Ill
    0.25
    eous
    0.25
    é¢ł
    0.25
     consect
    0.24
    olle
    0.24
    Ļ¶
    0.24
    --[
    0.24
    amient
    0.24
    Activations Density 5.127%

    No Known Activations