© 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. 141655
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ToolStrip
    -0.31
    iat
    -0.28
     apparent
    -0.28
     Forgotten
    -0.27
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.26
     Tos
    -0.26
    ä¸Ńåħ³
    -0.25
    çľ
    -0.25
    æ³»
    -0.25
    .pivot
    -0.24
    POSITIVE LOGITS
    amus
    0.29
    çļĦåĽŀçŃĶ
    0.28
    æºIJ
    0.27
    俦
    0.26
    nuts
    0.26
     sorts
    0.26
     quÃł
    0.26
    typescript
    0.25
    quia
    0.25
    atedRoute
    0.24
    Activations Density 20.390%

    No Known Activations