© 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. 107809
    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
    ware
    -0.31
     pract
    -0.27
    à¯ģ
    -0.26
    åĪ°äºĨ
    -0.25
    ton
    -0.25
    ↵↵
    -0.25
    .load
    -0.24
     series
    -0.24
    Ware
    -0.24
    wy
    -0.24
    POSITIVE LOGITS
    缴è¾ĸ
    0.27
    äºĭæ¥Ń
    0.26
    æĹģ
    0.26
    iasi
    0.26
    adow
    0.25
    apons
    0.25
    çļĦæĶ¿æ²»
    0.25
    OperationException
    0.24
    ä»İèĢĮ使
    0.24
     disap
    0.24
    Activations Density 14.800%

    No Known Activations