© 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. 141492
    Prev
    Next
    INDEX
    Explanations

    Sentence beginnings/determiners/comparatives

    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
     addAction
    -0.28
    çī¹ä»·
    -0.28
    æĸ°å¼Ģ
    -0.26
    LOY
    -0.26
    çļĦäºĭæĥħ
    -0.26
    -columns
    -0.25
     Royale
    -0.25
    hall
    -0.25
     yourselves
    -0.24
    jure
    -0.24
    POSITIVE LOGITS
    asco
    0.28
    缴æİ¥
    0.28
    leo
    0.26
    æµıè§ĪåĻ¨
    0.25
    _BROWSER
    0.25
    è¯ļ
    0.24
    æĪijçĪ±ä½ł
    0.24
    æ·ĭ
    0.23
    placed
    0.23
    æ´²
    0.23
    Activations Density 8.358%

    No Known Activations